跳转至

VoiceHubvad_auditok

AuditokVAD

Runs Auditok's weightless energy detector with conservative speech/silence durations.

Voice activity detectionVoiceHub-nativeenergy-vadParameters: WeightlessNot text-language conditionedTraining: inference-onlyLicense: Source terms require review

Parameter metadata: Weightless algorithm; the registered default has no model parameters.

Use this model
Resources
Upstream GitHub VoiceHub source

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 Auditok's weightless energy detector with conservative speech/silence durations.

Inputs and controls: Energy thresholds are recording-level heuristics and must be recalibrated after gain changes.

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(
    'auditok-energy-vad',
    model_type='vad_auditok',
    device="cpu",
    lazy_load=True,
)
output = model.detect(
    AUDIO_FILE,
    min_speech_duration_ms=200,
    min_silence_duration_ms=300,
    speech_pad_ms=20,
)
for segment in output.segments:
    print(segment.start, segment.end, segment.score)

Use authorized recordings. Version the implementation and configuration in production.

Overview

vad_auditok is a VoiceHub voice activity detection integration. This page is generated from its registry contract.

Property Value
Task Voice activity detection
Architecture energy-vad
Runtime VoiceHub-native
Languages Not text-language conditioned
Capabilities voice-activity-detection, energy-based, adaptive-threshold, algorithmic, voicehub-native
Reusable components —
Normalized output VADOutput

Language support

This weightless runtime does not select a spoken language and is not text-language conditioned; validate its implementation, configuration, and recording conditions for the target speech.

Paper and GitHub

Configuration

Load configuration without constructing the model:

from voicehub import AutoConfig

config = AutoConfig.for_model('vad_auditok')
print(config.model_type)
Property Value
Canonical model type vad_auditok
Configuration class AuditokVADConfig
Architecture class AuditokVADForVoiceActivityDetection

Processing

Create the registered processor without allocating model weights:

from voicehub import AutoProcessor

processor = AutoProcessor.from_pretrained(
    'auditok-energy-vad',
    model_type='vad_auditok',
)
print(type(processor).__name__)

Inference

The Usage example returns VADOutput through AutoModelForVoiceActivityDetection.

Input and output contract

Property Value
Label boundary No verified training dataset contract
Required training inputs —

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 inference-only
Family upstream-native
Recipe single-phase
Default phase default
Runtime identifier auditok-energy-vad
Native training graph no
Phase Kind Components Required inputs Loss keys
default objective — — loss, total_loss

This integration is inference-only. Choose a verified model from the training matrix.

Checkpoints, provenance, license, and limitations

Property Value
Runtime identifier auditok-energy-vad
Hugging Face ID Not published / not applicable
Not applicable: Auditok VAD is an energy-based detector with no model weights.
Checkpoint status Not applicable; this is a weightless algorithm with no checkpoint
Optional dependency extra Core package
Hardware and runtime Usage selects cpu; verify implementation-specific requirements
Real-checkpoint evidence Not applicable; version the implementation, configuration, and source provenance
Implementation voicehub.models.vad_auditok.modeling_vad_auditok.AuditokVADForVoiceActivityDetection
Configuration voicehub.models.vad_auditok.configuration_vad_auditok.AuditokVADConfig
Source provenance No integration-specific bundled SOURCE.json is declared for this registry entry.
License Source terms require review

This weightless runtime has no checkpoint license. Review the VoiceHub and upstream implementation terms before use.

Confirm the implementation revision, source provenance, access terms, and license.

Limitations

  • Weightless algorithm; the registered default has no model parameters.
  • 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 implementation and recording-condition validation.

Public API

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

Configuration

AuditokVADConfig

View source

AuditokVADConfig(**config_kwargs)

Parameters

  • **config_kwargs — Configuration fields validated by AuditokVADConfig.

Model

AuditokVADForVoiceActivityDetection

View source

AutoModelForVoiceActivityDetection.from_pretrained(
    pretrained_model_name_or_path,
    *,
    model_type='vad_auditok',
    config=None,
    **model_kwargs,
)

Parameters

  • pretrained_model_name_or_path — Runtime identifier for this weightless implementation.
  • model_type — Canonical model type; use 'vad_auditok'.
  • config — Optional preloaded AuditokVADConfig instance.
  • **model_kwargs — Model-specific loading arguments.
from voicehub import get_model_spec

spec = get_model_spec('vad_auditok')
print(spec.display_name, spec.task.value)
Purpose Public object
Discover get_model_spec('vad_auditok')
Load and run AutoModelForVoiceActivityDetection
Configure AuditokVADConfig
Process AutoProcessor
Model implementation AuditokVADForVoiceActivityDetection
Normalized output VADOutput
Training contract get_training_spec('vad_auditok')
Optimization lifecycle available_optimization_passes, apply_optimization_plan, optimization_manifest, restore_optimization_plan

See all model guides, inference, and the training matrix.