A model is still running

A model is still running or downloading. Leaving will stop the current operation. Stay on this page to let it finish.

Skip to content
LocalAI.toolsBeta

Join the waitlist

Get an email when the new apps and model runs launch.

No account needed.

pyannote Community 1

Estimate who spoke when locally using pyannote Community-1. Returns regular and exclusive speaker-turn timelines with anonymous speaker labels, not names or transcripts.

Desktop inferencePrivate · Runs on your computer
About this model

Estimate who spoke when locally using pyannote Community-1. Returns regular and exclusive speaker-turn timelines with anonymous speaker labels, not names or transcripts.

Created by
pyannote
License
CC-BY-4.0
Model released
Unknown
Source repository created
Apr 15, 2025
Model weights · FP32
32.6 MB

Best for

  • Creating speaker-turn timelines for authorized conversations
  • Preparing speaker-labeled transcription workflows
  • Comparing regular overlapping and exclusive nonoverlapping timelines

Keep in mind

  • Short turns, similar voices, overlap, noise, music and reverberation can cause missed speech, wrong boundaries or merged/split speakers.
  • Retained short synthetic conversation failed the frozen quality gate: automatic counting merged voices and known-count assignment also exceeded the error threshold. Longer synthetic turns passed; this does not establish broad meeting accuracy.
  • Speaker labels are anonymous clusters, not identity, gender, emotion or voice authentication. No transcription is generated.
  • Regular segments can overlap; exclusiveSegments chooses one speaker at a time and may simplify overlapping speech. Review timing/assignments.
  • The app accepts mono/stereo WAV, downmixes and resamples to16kHz. Full input/IPC, embeddings and clustering use memory/time with recording length; no fixed product duration cap.
  • Only FP32 CPU/Metal on the recorded M3 Max/macOS host is verified. Windows, Intel Mac, other Mac chips/OS/precision stacks remain unverified.
  • Model download requires accepting upstream Hugging Face conditions and a local HF login. Once installed inference is offline; telemetry is disabled.
  • App-owned isolated Python/framework packages are downloaded on request; system/user Python and global packages are not used.
  • Accuracy limitation: short synthetic two-speaker turns failed the DER gate, including known-speaker-count and stereo probes. Short-input coverage is structural only; longer-turn passing evidence does not establish short-turn speaker accuracy.

Processed on your deviceYour input is processed locally in the desktop app. Model and runtime files download from external hosts.

Target platforms · verification required

  • macos · aarch64, x86_64
  • windows · x86_64

Recommended configuration

FP32 · mps (verified platform only)

Sources & technical details
Original model
https://huggingface.co/pyannote/speaker-diarization-community-1
Release verification
Unknown
Release evidence
Exact original checkpoint public release date has not been verified. Repository creation, training, paper, artifact conversion and update dates are not release evidence.
Source updated
Sep 29, 2025
Native model files
https://huggingface.co/pyannote/speaker-diarization-community-1
Files updated
Sep 29, 2025
Artifact revision
3533c8cf8e369892e6b79ff1bf80f7b0286a54ee

Desktop app

Sample result

pyannote Community-1 — Speaker Diarization

Run pyannote Community 1 on your computer

Download the desktop app to load this model, provide input and view results locally.

Public desktop downloads are coming soon.

Device requirements

macOS Apple SiliconCPU / FP32Tested16.0 GiBRAM estimate
macOS Apple SiliconMPS / FP32Tested16.0 GiBRAM estimate
Windows Intel / AMDCPU / FP32Unverified16.0 GiBRAM estimate
macOS Intel / AMDCPU / FP32Unverified16.0 GiBRAM estimate
If your device falls short

MemoryAdvisory only: close other apps, reduce image/tile/token/batch settings or choose a smaller verified model/precision. CPU can need more RAM than GPU.

GPUIf the selected GPU runtime fails, existing CPU fallback may recover when enabled, but CPU has its own memory/runtime needs.

PlatformUse a compatible OS/architecture/runtime or another model. These estimates do not add hardware detection or block runs.

Benchmark evidence

Saved desktop measurements apply to the recorded hardware and runtime. Fallback cases report the device that actually ran; they do not prove GPU support on the requested device.

pyannote Community-1 — Speaker Diarization

71 configurations tested
Passed47
Failed24
TestedNov 2, 2026
Runtimepyannote.audio 4.0.7

Quality criteria

{ "version": 1, "scope": "Cleared synthetic built-in voices, exact assembled turn boundaries and250ms collar. Not natural speaker/meeting/multilingual certification.", "maximumDiarizationErrorRate": 0.25, "collarSeconds": 0.25, "ignoreOverlap": false, "requirements": [ "Finite sorted original regular/exclusive segments within duration", "Correct unique-speaker count on scoped nonempty reference cases", "Empty silence output", "Permutation-invariant DER with exact reference activity at20ms resolution", "Short input structural only; no accuracy claim", "Actual requested CPU/Metal neural placement, clustering remains CPU" ] }

PrecisionDeviceResultPlatformInference / loadTask metric
FP32mpsAcceleratedPassedVery fastmacos · aarch6439 ms / 0 ms0.013 RTF
FP32mpsAcceleratedPassedVery fastmacos · aarch64859 ms / 0 ms0.025 RTF
FP32mpsAcceleratedPassedVery fastmacos · aarch64860 ms / 0 ms0.025 RTF
FP32mpsAcceleratedPassedVery fastmacos · aarch64895 ms / 0 ms0.026 RTF
FP32mpsAcceleratedPassedVery fastmacos · aarch64911 ms / 0 ms0.026 RTF
FP32mpsAcceleratedPassedVery fastmacos · aarch64915 ms / 0 ms0.027 RTF
FP32mpsAcceleratedPassedVery fastmacos · aarch64920 ms / 0 ms0.027 RTF
FP32mpsAcceleratedPassedVery fastmacos · aarch64963 ms / 0 ms0.028 RTF
FP32mpsAcceleratedPassedVery fastmacos · aarch64661 ms / 0 ms0.036 RTF
FP32mpsAcceleratedPassedVery fastmacos · aarch641472 ms / 780 ms0.043 RTF
FP32mpsAcceleratedPassedVery fastmacos · aarch641501 ms / 768 ms0.044 RTF
FP32mpsAcceleratedPassedFastmacos · aarch646933 ms / 690 ms0.201 RTF
FP32mpsAcceleratedPassedSlowmacos · aarch64326 ms / 0 ms1.305 RTF
FP32cpuPassedVery fastmacos · aarch6448 ms / 0 ms0.016 RTF
FP32cpuPassedVery fastmacos · aarch6451 ms / 0 ms0.017 RTF
FP32cpuPassedVery fastmacos · aarch6452 ms / 0 ms0.017 RTF
FP32cpuPassedVery fastmacos · aarch6453 ms / 0 ms0.018 RTF
FP32cpuPassedVery fastmacos · aarch64232 ms / 0 ms0.034 RTF
FP32cpuPassedVery fastmacos · aarch64340 ms / 0 ms0.049 RTF
FP32cpuPassedVery fastmacos · aarch64732 ms / 0 ms0.058 RTF
FP32cpuPassedVery fastmacos · aarch641242 ms / 0 ms0.098 RTF
FP32cpuPassedFastmacos · aarch646175 ms / 0 ms0.332 RTF
FP32cpuPassedFastmacos · aarch6414357 ms / 0 ms0.417 RTF
FP32cpuPassedFastmacos · aarch6414567 ms / 0 ms0.423 RTF
FP32cpuPassedFastmacos · aarch6414671 ms / 651 ms0.426 RTF
FP32cpuPassedFastmacos · aarch6414845 ms / 0 ms0.431 RTF
FP32cpuPassedFastmacos · aarch6414980 ms / 0 ms0.435 RTF
FP32cpuPassedFastmacos · aarch6414997 ms / 665 ms0.435 RTF
FP32cpuPassedFastmacos · aarch6415170 ms / 0 ms0.440 RTF
FP32cpuPassedFastmacos · aarch6415362 ms / 0 ms0.446 RTF
FP32cpuPassedFastmacos · aarch6415400 ms / 0 ms0.447 RTF
FP32cpuPassedFastmacos · aarch6415807 ms / 685 ms0.459 RTF
FP32cpuPassedModeratemacos · aarch6413551 ms / 0 ms0.729 RTF
FP32cpuPassedModeratemacos · aarch64215 ms / 0 ms0.859 RTF
FP32cpuPassedModeratemacos · aarch64224 ms / 0 ms0.898 RTF
FP32cpuPassedModeratemacos · aarch6431875 ms / 637 ms0.926 RTF
FP32cpuPassedModeratemacos · aarch6432034 ms / 0 ms0.930 RTF
FP32cpuPassedModeratemacos · aarch6432163 ms / 0 ms0.934 RTF
FP32cpuPassedModeratemacos · aarch6432225 ms / 0 ms0.936 RTF
FP32cpuPassedModeratemacos · aarch6432258 ms / 660 ms0.937 RTF
FP32cpuPassedModeratemacos · aarch6432265 ms / 0 ms0.937 RTF
FP32cpuPassedModeratemacos · aarch6432763 ms / 0 ms0.951 RTF
FP32cpuPassedModeratemacos · aarch6433595 ms / 0 ms0.975 RTF
FP32cpuPassedModeratemacos · aarch6433980 ms / 688 ms0.987 RTF
FP32cpuPassedModeratemacos · aarch6434400 ms / 0 ms0.999 RTF
FP32cpuPassedSlowmacos · aarch64348 ms / 0 ms1.391 RTF
FP32cpuPassedSlowmacos · aarch64348 ms / 0 ms1.392 RTF
FP32cpuFailed—macos · aarch641742 ms / 3873 ms0.138 RTF
FP32cpuFailed—macos · aarch641296 ms / 0 ms0.103 RTF
FP32cpuFailed—macos · aarch641468 ms / 0 ms0.116 RTF
FP32cpuFailed—macos · aarch641296 ms / 0 ms0.103 RTF
FP32cpuFailed—macos · aarch641266 ms / 0 ms0.100 RTF
FP32cpuFailed—macos · aarch641508 ms / 674 ms0.120 RTF
FP32cpuFailed—macos · aarch641259 ms / 0 ms0.100 RTF
FP32cpuFailed—macos · aarch641245 ms / 0 ms0.099 RTF
FP32cpuFailed—macos · aarch641435 ms / 644 ms0.114 RTF
FP32cpuFailed—macos · aarch641272 ms / 0 ms0.101 RTF
FP32cpuFailed—macos · aarch641211 ms / 0 ms0.096 RTF
FP32cpuFailed—macos · aarch641231 ms / 0 ms0.098 RTF
FP32cpuFailed—macos · aarch641203 ms / 0 ms0.095 RTF
FP32cpuFailed—macos · aarch641244 ms / 0 ms0.099 RTF
FP32cpuFailed—macos · aarch641215 ms / 0 ms0.096 RTF
FP32cpuFailed—macos · aarch641202 ms / 0 ms0.095 RTF
FP32cpuFailed—macos · aarch64846 ms / 642 ms0.067 RTF
FP32cpuFailed—macos · aarch64791 ms / 0 ms0.063 RTF
FP32cpuFailed—macos · aarch64805 ms / 0 ms0.064 RTF
FP32cpuFailed—macos · aarch64733 ms / 0 ms0.058 RTF
FP32cpuFailed—macos · aarch64718 ms / 0 ms0.057 RTF
FP32cpuFailed—macos · aarch64846 ms / 659 ms0.067 RTF
FP32cpuFailed—macos · aarch64729 ms / 0 ms0.058 RTF
FP32cpuFailed—macos · aarch64735 ms / 0 ms0.058 RTF
Test setup & sample details
Quality gate
{ "version": 1, "scope": "Cleared synthetic built-in voices, exact assembled turn boundaries and250ms collar. Not natural speaker/meeting/multilingual certification.", "maximumDiarizationErrorRate": 0.25, "collarSeconds": 0.25, "ignoreOverlap": false, "requirements": [ "Finite sorted original regular/exclusive segments within duration", "Correct unique-speaker count on scoped nonempty reference cases", "Empty silence output", "Permutation-invariant DER with exact reference activity at20ms resolution", "Short input structural only; no accuracy claim", "Actual requested CPU/Metal neural placement, clustering remains CPU" ] }
Tested
2026-11-02T00:39:11.379675+00:00
Environment
{ "os": "macos", "arch": "aarch64", "hardware": "Apple M3 Max", "osVersion": "27.2" }
Runtime
pyannote.audio 4.0.7
Artifact revision
3533c8cf8e369892e6b79ff1bf80f7b0286a54ee
Fixture
{
  "file": "model-samples/desktop/pyannote/pyannote-long-two-speakers.wav",
  "url": "https://assets.localai.tools/samples/v1/files/e600857dcab01289b7134862a783827b689da90990ece36b5e5c030b97d285aa/pyannote-long-two-speakers.wav",
  "size": 2204200,
  "sha1": "438e52c06caa4ce65108d946d91c6ba3bbfce793",
  "sha256": "e600857dcab01289b7134862a783827b689da90990ece36b5e5c030b97d285aa"
}
Rerun when
Pipeline/checkpoint/PLDA revision; Pinned runtime version; Fixture/reference/quality gate; Preprocessing/clustering/settings behavior; Relevant backend/OS behavior
Per-case quality & failure details
[
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 636.7686670055264,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 31875.305040994135,
      "inferenceMs": 31875.305040994135,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.9255483016458381,
      "audioSecondsPerSecond": 1.0804406406686389,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 32512.07370799966,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "moderate"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 32034.011125004326,
      "inferenceMs": 32034.011125004326,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.9301565758671383,
      "audioSecondsPerSecond": 1.0750878141862839,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 32034.011125004326,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "moderate"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 32762.55591699737,
      "inferenceMs": 32762.55591699737,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.9513109897318802,
      "audioSecondsPerSecond": 1.051180960583502,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 32762.55591699737,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "moderate"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03074866310160428,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 32264.588124999136,
      "inferenceMs": 32264.588124999136,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.9368517322105624,
      "audioSecondsPerSecond": 1.0674047617336793,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 32264.588124999136,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "moderate"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.0024875621890547263,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 1,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 13551.428874998237,
      "inferenceMs": 13551.428874998237,
      "audioSeconds": 18.5855,
      "realTimeFactor": 0.7291398603749287,
      "audioSecondsPerSecond": 1.371478990993296,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 13551.428874998237,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "moderate"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {},
      "referenceSpeakers": 0,
      "hypothesisSpeakers": 0
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 51.984290999826044,
      "inferenceMs": 51.984290999826044,
      "audioSeconds": 3,
      "realTimeFactor": 0.017328096999942016,
      "audioSecondsPerSecond": 57.70974158347257,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 51.984290999826044,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 347.794832996442,
      "inferenceMs": 347.794832996442,
      "audioSeconds": 0.25,
      "realTimeFactor": 1.391179331985768,
      "audioSecondsPerSecond": 0.7188145891821157,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 1,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 347.794832996442,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "slow"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 32225.082083001325,
      "inferenceMs": 32225.082083001325,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.9357046137742432,
      "audioSecondsPerSecond": 1.0687133367510244,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 32225.082083001325,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "moderate"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 32162.912041996606,
      "inferenceMs": 32162.912041996606,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.933899411414888,
      "audioSecondsPerSecond": 1.0707791307898646,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 32162.912041996606,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "moderate"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 659.7587920041406,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 32258.333999998285,
      "inferenceMs": 32258.333999998285,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.9366701341124305,
      "audioSecondsPerSecond": 1.0676117061718633,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 32918.092792002426,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "moderate"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 34400.31525000086,
      "inferenceMs": 34400.31525000086,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.9988658403353968,
      "audioSecondsPerSecond": 1.0011354474432945,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 34400.31525000086,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "moderate"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 687.8951670005335,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 33980.16483399988,
      "inferenceMs": 33980.16483399988,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.9866661295101865,
      "audioSecondsPerSecond": 1.0135140652861296,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 34668.06000100041,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "moderate"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 33594.51870799967,
      "inferenceMs": 33594.51870799967,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.9754683035914464,
      "audioSecondsPerSecond": 1.0251486350896626,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 33594.51870799967,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "moderate"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 685.0272079973365,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 15806.844833001378,
      "inferenceMs": 15806.844833001378,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.45897594927321933,
      "audioSecondsPerSecond": 2.178763400529991,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 16491.872040998715,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 14844.762542001263,
      "inferenceMs": 14844.762542001263,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.43104041644197266,
      "audioSecondsPerSecond": 2.3199680629823756,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 14844.762542001263,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 15400.196374997904,
      "inferenceMs": 15400.196374997904,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.4471682884778804,
      "audioSecondsPerSecond": 2.2362945355626795,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 15400.196374997904,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03074866310160428,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 14980.300000002899,
      "inferenceMs": 14980.300000002899,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.4349759541223643,
      "audioSecondsPerSecond": 2.2989776573228395,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 14980.300000002899,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.0024875621890547263,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 1,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 6175.2869590054615,
      "inferenceMs": 6175.2869590054615,
      "audioSeconds": 18.5855,
      "realTimeFactor": 0.3322636979906627,
      "audioSecondsPerSecond": 3.009657708763905,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 6175.2869590054615,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {},
      "referenceSpeakers": 0,
      "hypothesisSpeakers": 0
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 47.95412500243401,
      "inferenceMs": 47.95412500243401,
      "audioSeconds": 3,
      "realTimeFactor": 0.01598470833414467,
      "audioSecondsPerSecond": 62.55979021299479,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 47.95412500243401,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 224.4265830013319,
      "inferenceMs": 224.4265830013319,
      "audioSeconds": 0.25,
      "realTimeFactor": 0.8977063320053276,
      "audioSecondsPerSecond": 1.113950035047837,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 1,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 224.4265830013319,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "moderate"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 15169.502707998618,
      "inferenceMs": 15169.502707998618,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.4404697445292958,
      "audioSecondsPerSecond": 2.270303493986043,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 15169.502707998618,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 14567.277415997523,
      "inferenceMs": 14567.277415997523,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.4229832108160361,
      "audioSecondsPerSecond": 2.3641600291197373,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 14567.277415997523,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 651.0132499970496,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 14671.245459001511,
      "inferenceMs": 14671.245459001511,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.4260020821806874,
      "audioSecondsPerSecond": 2.347406366844595,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 15322.25870899856,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 15361.747791001108,
      "inferenceMs": 15361.747791001108,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.4460518749542089,
      "audioSecondsPerSecond": 2.2418917084535486,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 15361.747791001108,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 665.2754999959143,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 14997.117999999318,
      "inferenceMs": 14997.117999999318,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.43546429051047875,
      "audioSecondsPerSecond": 2.2963995482333046,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 15662.393499995233,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 14357.023124997795,
      "inferenceMs": 14357.023124997795,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.41687815545426693,
      "audioSecondsPerSecond": 2.398782442582803,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 14357.023124997795,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 690.4295000058482,
      "provider": "Metal/MPS",
      "placement": {
        "segmentation": {
          "mps:0/torch.float32": 52
        },
        "embedding": {
          "mps:0/torch.float32": 110
        }
      },
      "acceleration": "partial",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 6932.668959001603,
      "inferenceMs": 6932.668959001603,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.20130066120542556,
      "audioSecondsPerSecond": 4.967693568475211,
      "activationPlacement": {
        "segmentation": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        },
        "embedding": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": 4837818368,
      "device": "mps",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 7623.098459007451,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "Metal/MPS",
      "placement": {
        "segmentation": {
          "mps:0/torch.float32": 52
        },
        "embedding": {
          "mps:0/torch.float32": 110
        }
      },
      "acceleration": "partial",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 859.4651249950402,
      "inferenceMs": 859.4651249950402,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.024955886249243497,
      "audioSecondsPerSecond": 40.070706766837965,
      "activationPlacement": {
        "segmentation": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        },
        "embedding": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": 5911560192,
      "device": "mps",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 859.4651249950402,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "Metal/MPS",
      "placement": {
        "segmentation": {
          "mps:0/torch.float32": 52
        },
        "embedding": {
          "mps:0/torch.float32": 110
        }
      },
      "acceleration": "partial",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 911.2784169992665,
      "inferenceMs": 911.2784169992665,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.026460364539114503,
      "audioSecondsPerSecond": 37.79237427064809,
      "activationPlacement": {
        "segmentation": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        },
        "embedding": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": 5911560192,
      "device": "mps",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 911.2784169992665,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03074866310160428,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "Metal/MPS",
      "placement": {
        "segmentation": {
          "mps:0/torch.float32": 52
        },
        "embedding": {
          "mps:0/torch.float32": 110
        }
      },
      "acceleration": "partial",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 894.9942920007743,
      "inferenceMs": 894.9942920007743,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.025987530029240494,
      "audioSecondsPerSecond": 38.47999401539223,
      "activationPlacement": {
        "segmentation": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        },
        "embedding": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": 5911560192,
      "device": "mps",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 894.9942920007743,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.0024875621890547263,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 1,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "Metal/MPS",
      "placement": {
        "segmentation": {
          "mps:0/torch.float32": 52
        },
        "embedding": {
          "mps:0/torch.float32": 110
        }
      },
      "acceleration": "partial",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 660.7668750002631,
      "inferenceMs": 660.7668750002631,
      "audioSeconds": 18.5855,
      "realTimeFactor": 0.03555281671196702,
      "audioSecondsPerSecond": 28.1271666349688,
      "activationPlacement": {
        "segmentation": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        },
        "embedding": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": 6144278528,
      "device": "mps",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 660.7668750002631,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {},
      "referenceSpeakers": 0,
      "hypothesisSpeakers": 0
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "Metal/MPS",
      "placement": {
        "segmentation": {
          "mps:0/torch.float32": 52
        },
        "embedding": {
          "mps:0/torch.float32": 110
        }
      },
      "acceleration": "partial",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 38.884207999217324,
      "inferenceMs": 38.884207999217324,
      "audioSeconds": 3,
      "realTimeFactor": 0.012961402666405775,
      "audioSecondsPerSecond": 77.15214361728508,
      "activationPlacement": {
        "segmentation": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": 6144278528,
      "device": "mps",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 38.884207999217324,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "Metal/MPS",
      "placement": {
        "segmentation": {
          "mps:0/torch.float32": 52
        },
        "embedding": {
          "mps:0/torch.float32": 110
        }
      },
      "acceleration": "partial",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 326.33870800054865,
      "inferenceMs": 326.33870800054865,
      "audioSeconds": 0.25,
      "realTimeFactor": 1.3053548320021946,
      "audioSecondsPerSecond": 0.7660752275809699,
      "activationPlacement": {
        "segmentation": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        },
        "embedding": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        }
      },
      "numSpeakers": 1,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": 6144540672,
      "device": "mps",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 326.33870800054865,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "slow"
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "Metal/MPS",
      "placement": {
        "segmentation": {
          "mps:0/torch.float32": 52
        },
        "embedding": {
          "mps:0/torch.float32": 110
        }
      },
      "acceleration": "partial",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 915.4091250020429,
      "inferenceMs": 915.4091250020429,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.026580305972510907,
      "audioSecondsPerSecond": 37.62183930592034,
      "activationPlacement": {
        "segmentation": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        },
        "embedding": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": 6144540672,
      "device": "mps",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 915.4091250020429,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "Metal/MPS",
      "placement": {
        "segmentation": {
          "mps:0/torch.float32": 52
        },
        "embedding": {
          "mps:0/torch.float32": 110
        }
      },
      "acceleration": "partial",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 963.4044589984114,
      "inferenceMs": 963.4044589984114,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.02797392400409158,
      "audioSecondsPerSecond": 35.747576916764906,
      "activationPlacement": {
        "segmentation": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        },
        "embedding": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": 6144540672,
      "device": "mps",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 963.4044589984114,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 768.4797920010169,
      "provider": "Metal/MPS",
      "placement": {
        "segmentation": {
          "mps:0/torch.float32": 52
        },
        "embedding": {
          "mps:0/torch.float32": 110
        }
      },
      "acceleration": "partial",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1500.753790998715,
      "inferenceMs": 1500.753790998715,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.04357668485559668,
      "audioSecondsPerSecond": 22.948051310322818,
      "activationPlacement": {
        "segmentation": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        },
        "embedding": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": 4837818368,
      "device": "mps",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 2269.233582999732,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "Metal/MPS",
      "placement": {
        "segmentation": {
          "mps:0/torch.float32": 52
        },
        "embedding": {
          "mps:0/torch.float32": 110
        }
      },
      "acceleration": "partial",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 919.8081669965177,
      "inferenceMs": 919.8081669965177,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.026708038894332944,
      "audioSecondsPerSecond": 37.44191042840608,
      "activationPlacement": {
        "segmentation": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        },
        "embedding": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": 5911560192,
      "device": "mps",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 919.8081669965177,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 779.5134580010199,
      "provider": "Metal/MPS",
      "placement": {
        "segmentation": {
          "mps:0/torch.float32": 52
        },
        "embedding": {
          "mps:0/torch.float32": 110
        }
      },
      "acceleration": "partial",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1472.2144580009626,
      "inferenceMs": 1472.2144580009626,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.04274800161155545,
      "audioSecondsPerSecond": 23.392906388627164,
      "activationPlacement": {
        "segmentation": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        },
        "embedding": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": 4837818368,
      "device": "mps",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 2251.7279160019825,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "mps",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.03609625668449198,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "Metal/MPS",
      "placement": {
        "segmentation": {
          "mps:0/torch.float32": 52
        },
        "embedding": {
          "mps:0/torch.float32": 110
        }
      },
      "acceleration": "partial",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 860.157082999649,
      "inferenceMs": 860.157082999649,
      "audioSeconds": 34.439375,
      "realTimeFactor": 0.024975978309700712,
      "audioSecondsPerSecond": 40.038471670661174,
      "activationPlacement": {
        "segmentation": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        },
        "embedding": {
          "input": "mps:0",
          "outputs": [
            "mps:0"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": 5911560192,
      "device": "mps",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 860.157082999649,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 3872.5157079970813,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1742.2865000044112,
      "inferenceMs": 1742.2865000044112,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.13813281799747573,
      "audioSecondsPerSecond": 7.239409247542276,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 5614.8022080014925,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.2938271604938272,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1296.280292001029,
      "inferenceMs": 1296.280292001029,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.1027723337397377,
      "audioSecondsPerSecond": 9.73024513126671,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 1296.280292001029,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.2938271604938272,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1468.2790829974692,
      "inferenceMs": 1468.2790829974692,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.11640882675764089,
      "audioSecondsPerSecond": 8.590413870264022,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 1468.2790829974692,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.06419753086419754,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A",
        "SPEAKER_01": "B"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1241.992916999152,
      "inferenceMs": 1241.992916999152,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.09846829528757955,
      "audioSecondsPerSecond": 10.155553085178031,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 1241.992916999152,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 1,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 340.01370899932226,
      "inferenceMs": 340.01370899932226,
      "audioSeconds": 6.9285,
      "realTimeFactor": 0.04907464949113405,
      "audioSecondsPerSecond": 20.377119559064045,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 340.01370899932226,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {},
      "referenceSpeakers": 0,
      "hypothesisSpeakers": 0
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 52.91412500082515,
      "inferenceMs": 52.91412500082515,
      "audioSeconds": 3,
      "realTimeFactor": 0.017638041666941717,
      "audioSecondsPerSecond": 56.69563656118697,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 52.91412500082515,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 348.0488749992219,
      "inferenceMs": 348.0488749992219,
      "audioSeconds": 0.25,
      "realTimeFactor": 1.3921954999968875,
      "audioSecondsPerSecond": 0.7182899240819524,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 1,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 348.0488749992219,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "slow"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1295.559582998976,
      "inferenceMs": 1295.559582998976,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.1027151941330143,
      "audioSecondsPerSecond": 9.735657985565584,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 1295.559582998976,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1266.3162500030012,
      "inferenceMs": 1266.3162500030012,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.1003967097767604,
      "audioSecondsPerSecond": 9.960485779101473,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 1266.3162500030012,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 674.1718749981374,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1507.9122500028461,
      "inferenceMs": 1507.9122500028461,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.1195510430605299,
      "audioSecondsPerSecond": 8.364627981486452,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 2182.0841250009835,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1259.0466669935267,
      "inferenceMs": 1259.0466669935267,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.09982035910954079,
      "audioSecondsPerSecond": 10.017996417971416,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 1259.0466669935267,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1244.7428749946994,
      "inferenceMs": 1244.7428749946994,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.09868631881430648,
      "audioSecondsPerSecond": 10.133116849577236,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 1244.7428749946994,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 643.5799160026363,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1434.6612919980544,
      "inferenceMs": 1434.6612919980544,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.11374352446345012,
      "audioSecondsPerSecond": 8.791709283822446,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 2078.2412080006907,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1271.678790995793,
      "inferenceMs": 1271.678790995793,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.10082186539781322,
      "audioSecondsPerSecond": 9.918483416809401,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 1271.678790995793,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1210.5147500042222,
      "inferenceMs": 1210.5147500042222,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.09597262771947651,
      "audioSecondsPerSecond": 10.419637596283735,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 1210.5147500042222,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1230.658583001059,
      "inferenceMs": 1230.658583001059,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.09756968102679225,
      "audioSecondsPerSecond": 10.249085468726744,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 1230.658583001059,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1202.7901250039577,
      "inferenceMs": 1202.7901250039577,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.09536020018860969,
      "audioSecondsPerSecond": 10.486555166852986,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 1202.7901250039577,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1244.486041003256,
      "inferenceMs": 1244.486041003256,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.09866595637506614,
      "audioSecondsPerSecond": 10.13520809749846,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 1244.486041003256,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1215.1864159968682,
      "inferenceMs": 1215.1864159968682,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.09634300904786626,
      "audioSecondsPerSecond": 10.37958031291267,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 1215.1864159968682,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 1202.3990410016268,
      "inferenceMs": 1202.3990410016268,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.09532919407376259,
      "audioSecondsPerSecond": 10.489965951314273,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 1,
      "totalMs": 1202.3990410016268,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 642.2749999983353,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 845.7603749993723,
      "inferenceMs": 845.7603749993723,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.06705399137797907,
      "audioSecondsPerSecond": 14.913355334256895,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 1488.0353749977075,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.2938271604938272,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 790.5894579962478,
      "inferenceMs": 790.5894579962478,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.062679903512908,
      "audioSecondsPerSecond": 15.95407688836127,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 790.5894579962478,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.2938271604938272,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "B",
        "SPEAKER_01": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 804.9752089937101,
      "inferenceMs": 804.9752089937101,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.06382044172191349,
      "audioSecondsPerSecond": 15.668960806591196,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 804.9752089937101,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0.06419753086419754,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A",
        "SPEAKER_01": "B"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 2
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 732.0930409987341,
      "inferenceMs": 732.0930409987341,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.058042161716365614,
      "audioSecondsPerSecond": 17.228855205061034,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 2,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 732.0930409987341,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 1,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 232.4236659987946,
      "inferenceMs": 232.4236659987946,
      "audioSeconds": 6.9285,
      "realTimeFactor": 0.03354602958775992,
      "audioSecondsPerSecond": 29.809787098168965,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 232.4236659987946,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true,
      "diarizationErrorRate": 0,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {},
      "referenceSpeakers": 0,
      "hypothesisSpeakers": 0
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 51.44537500018487,
      "inferenceMs": 51.44537500018487,
      "audioSeconds": 3,
      "realTimeFactor": 0.017148458333394956,
      "audioSecondsPerSecond": 58.31427995206993,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 51.44537500018487,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "pass",
    "quality": {
      "passed": true,
      "validTimeline": true
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 214.87175000220304,
      "inferenceMs": 214.87175000220304,
      "audioSeconds": 0.25,
      "realTimeFactor": 0.8594870000088122,
      "audioSecondsPerSecond": 1.1634847298327342,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": 1,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 214.87175000220304,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "moderate"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 732.8062920059892,
      "inferenceMs": 732.8062920059892,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.058098710034665414,
      "audioSecondsPerSecond": 17.212086110058827,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 732.8062920059892,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 717.7922920018318,
      "inferenceMs": 717.7922920018318,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.056908362677911446,
      "audioSecondsPerSecond": 17.572109843675797,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 717.7922920018318,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 659.4564170009107,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 845.7736659984221,
      "inferenceMs": 845.7736659984221,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.06705504512152398,
      "audioSecondsPerSecond": 14.913120976769134,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 1505.2300829993328,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 728.8945410036831,
      "inferenceMs": 728.8945410036831,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.057788576661508,
      "audioSecondsPerSecond": 17.304458039474145,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 728.8945410036831,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  },
  {
    "precision": "fp32",
    "device": "cpu",
    "status": "fail",
    "quality": {
      "passed": false,
      "validTimeline": true,
      "diarizationErrorRate": 0.4617283950617284,
      "maximumDiarizationErrorRate": 0.25,
      "collarSeconds": 0.25,
      "evaluationStepSeconds": 0.02,
      "speakerMapping": {
        "SPEAKER_00": "A"
      },
      "referenceSpeakers": 2,
      "hypothesisSpeakers": 1
    },
    "runtime": {
      "engine": "pyannote.audio",
      "version": "4.0.7",
      "torchVersion": "2.10.0",
      "loadMs": 0,
      "provider": "PyTorch CPU",
      "placement": {
        "segmentation": {
          "cpu/torch.float32": 52
        },
        "embedding": {
          "cpu/torch.float32": 110
        }
      },
      "acceleration": "cpu",
      "accelerationDetails": "Segmentation and speaker-embedding networks on selected device; decoding, resample, clustering/PLDA and timeline assembly on CPU",
      "telemetryEnabled": false,
      "durationMs": 735.4196250016685,
      "inferenceMs": 735.4196250016685,
      "audioSeconds": 12.613125,
      "realTimeFactor": 0.05830590159073731,
      "audioSecondsPerSecond": 17.150922508998022,
      "activationPlacement": {
        "segmentation": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        },
        "embedding": {
          "input": "cpu",
          "outputs": [
            "cpu"
          ]
        }
      },
      "numSpeakers": null,
      "minSpeakers": null,
      "maxSpeakers": null,
      "driverAllocatedMemoryBytes": null,
      "device": "cpu",
      "precision": "fp32",
      "cpuThreads": 4,
      "totalMs": 735.4196250016685,
      "artifactRevision": "3533c8cf8e369892e6b79ff1bf80f7b0286a54ee",
      "fallback": false,
      "grade": "fast"
    }
  }
]

Something not quite right?

Tell us what happened with pyannote Community 1. Loading, results, or the page itself—we’re here for all of it.

Attachments Optional

Up to 3 files · 50 MB each

Browser, OS, CPU/GPU, memory, screen, storage, and network details are included automatically. Model inputs, results, and browsing history are not collected.