pyannotesegmentation-3.0

PyannoteSegmentationVAD¶

Runs pyannote segmentation 3.0 as VAD with hysteresis and frame evidence enabled.

Voice activity detectionVoiceHub-nativepyannetParameters: Not reportedNot text-language conditionedTraining: nativeLicense: Checkpoint-specific

Parameter metadata: Not reported: the audited metadata available for the registered default does not provide an exact parameter total.

Use this model Checkpoint

Resources

Usage¶

Complete the VoiceHub installation once, then run this repository-authored example. Model pages intentionally contain no package-install command.

This example is maintained against VoiceHub's public API; it is not copied from an upstream demo or package README.

Model-specific path: Runs pyannote segmentation 3.0 as VAD with hysteresis and frame evidence enabled.

Inputs and controls: Segmentation scores are converted to speech regions; they are not diarization labels by themselves.

from pathlib import Path

from voicehub import AutoModelForVoiceActivityDetection

AUDIO_FILE = Path("speech.wav")
if not AUDIO_FILE.is_file():
    raise FileNotFoundError(AUDIO_FILE)

model = AutoModelForVoiceActivityDetection.from_pretrained(
    'pyannote/segmentation-3.0',
    model_type='vad_pyannote_segmentation',
    device="cpu",
    lazy_load=True,
)
output = model.detect(
    AUDIO_FILE,
    onset=0.6,
    offset=0.4,
    return_frames=True,
)
for segment in output.segments:
    print(segment.start, segment.end, segment.score)

Use authorized recordings. Verify hardware needs and pin a revision in production.

Overview¶

vad_pyannote_segmentation is a VoiceHub voice activity detection integration. This page is generated from its registry contract. Open the vad_pyannote_segmentation Colab notebook.

Property	Value
Task	Voice activity detection
Architecture	`pyannet`
Runtime	`VoiceHub-native`
Languages	Not text-language conditioned
Capabilities	`voice-activity-detection`, `voicehub-native`, `gated-checkpoint`, `trusted-checkpoint-conversion`, `safetensors`, `powerset`, `frame-scores`, `fine-tuning`
Reusable components	—
Normalized output	`VADOutput`

Language support¶

The public VAD contract does not select a spoken language; validate checkpoint acoustic coverage on the target languages and recording conditions.

Paper and GitHub¶

Paper: pyannote.audio: neural building blocks for speaker diarization
Upstream GitHub: pyannote.audio
VoiceHub source: VoiceHub model implementation

Configuration¶

Load configuration without constructing the model:

from voicehub import AutoConfig

config = AutoConfig.for_model('vad_pyannote_segmentation')
print(config.model_type)

Property	Value
Canonical model type	`vad_pyannote_segmentation`
Configuration class	`PyannoteSegmentationVADConfig`
Architecture class	`PyannoteSegmentationVADForVoiceActivityDetection`

Processing¶

Create the registered processor without allocating model weights:

from voicehub import AutoProcessor

processor = AutoProcessor.from_pretrained(
    'pyannote/segmentation-3.0',
    model_type='vad_pyannote_segmentation',
)
print(type(processor).__name__)

Inference¶

The Usage example returns VADOutput through AutoModelForVoiceActivityDetection.

Input and output contract¶

Property	Value
Label boundary	Clip-, frame-, or segment-level labels
Required training inputs	`waveforms`, `labels`

Use authorized audio and preserve annotation provenance. See the ASR and VAD data workflow.

Training and optimization¶

Use available_optimization_passes() to discover reversible public passes. Unsupported runtime or hardware fails closed before mutation.

Training contract¶

Property	Value
Support	`native`
Family	`frame-classification`
Recipe	`single-phase`
Default phase	`powerset_segmentation`
Training checkpoint	`pyannote/segmentation-3.0`
Native training graph	`yes`

Phase	Kind	Components	Required inputs	Loss keys
`powerset_segmentation`	objective	`model`	`waveforms`, `labels`	`loss`

The integration accepts its declared source or prepared contract directly. Call model.validate_training_support() first, then follow the training workflow.

Checkpoints, provenance, license, and limitations¶

Property	Value
Default checkpoint	`pyannote/segmentation-3.0`
Hugging Face ID	`pyannote/segmentation-3.0` Repository availability verified through the Hugging Face model API on 2026-08-11; pin a revision before production use.
Checkpoint status	Registry default; pin an immutable revision for production and reproducible evidence
Optional dependency extra	Core package
Hardware and runtime	Usage selects `cpu`; verify checkpoint-specific requirements
Real-checkpoint evidence	Release evidence; a registry default alone is not execution evidence
Implementation	`voicehub.models.vad_pyannote_segmentation.modeling_vad_pyannote_segmentation.PyannoteSegmentationVADForVoiceActivityDetection`
Configuration	`voicehub.models.vad_pyannote_segmentation.configuration_vad_pyannote_segmentation.PyannoteSegmentationVADConfig`
Source provenance	`voicehub/architectures/pyannet/SOURCE.json`
License	Checkpoint-specific

No VoiceHub-specific license override is registered. Verify the checkpoint and upstream source terms before use.

Confirm the checkpoint revision, access terms, provenance, and license.

Limitations¶

No integration-specific checkpoint limitation is registered. Verify the selected checkpoint revision and its documented runtime requirements.
Validate memory, precision, and optional dependencies on the target system.
Public optimizations fail closed when the runtime or hardware cannot satisfy their validation contract; an unavailable pass is not reported as applied.
Contract tests do not replace the linked released-checkpoint evidence.

Public API¶

Use the stable configuration, processor, and task-model facades below.

Configuration