Saltar a contenido

patrickvonplatenwavlm-libri-clean-100h-base-plus

WavLM

Runs the registered WavLM CTC checkpoint with greedy single-beam decoding.

Automatic speech recognitionVoiceHub-nativewavlmParameters: Not reportedLanguage: enTraining: 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
Paper Upstream GitHub VoiceHub source Open in Colab

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 the registered WavLM CTC checkpoint with greedy single-beam decoding.

Inputs and controls: This community LibriSpeech checkpoint is English-specific even though the WavLM architecture is general.

from pathlib import Path

from voicehub import AutoModelForSpeechRecognition

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

model = AutoModelForSpeechRecognition.from_pretrained(
    'patrickvonplaten/wavlm-libri-clean-100h-base-plus',
    model_type='asr_wavlm',
    device="cuda",
    lazy_load=True,
)
output = model.transcribe(
    AUDIO_FILE,
    language="en",
    num_beams=1,
)
print(output.text)
for segment in output.segments:
    print(segment.start, segment.end, segment.text, segment.confidence)

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

Overview

asr_wavlm is a VoiceHub automatic speech recognition integration. This page is generated from its registry contract. Open the asr_wavlm Colab notebook.

Property Value
Task Automatic speech recognition
Architecture wavlm
Runtime VoiceHub-native
Languages en
Capabilities automatic-speech-recognition, timestamps, safetensors, fine-tuning, voicehub-native
Reusable components —
Normalized output ASROutput

Language support

Supported language abbreviations

en

Paper and GitHub

Configuration

Load configuration without constructing the model:

from voicehub import AutoConfig

config = AutoConfig.for_model('asr_wavlm')
print(config.model_type)
Property Value
Canonical model type asr_wavlm
Configuration class WavLMASRConfig
Architecture class WavLMForSpeechRecognition

Processing

Create the registered processor without allocating model weights:

from voicehub import AutoProcessor

processor = AutoProcessor.from_pretrained(
    'patrickvonplaten/wavlm-libri-clean-100h-base-plus',
    model_type='asr_wavlm',
)
print(type(processor).__name__)

Inference

The Usage example returns ASROutput through AutoModelForSpeechRecognition.

Input and output contract

Property Value
Readiness integrated-raw
Data architecture ctc
Sample rate 16,000 Hz
Contract getter get_asr_dataset_spec('asr_wavlm')
Variant Required fields One of Boundary Other rules
raw-audio audio text / transcription / transcript Source at most one: text / transcription / transcript
waveform-ctc input_values, labels — Prepared —

WavLM waveform and CTC transcript records. See the 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 ctc
Recipe single-phase
Default phase speech_recognition
Training checkpoint patrickvonplaten/wavlm-libri-clean-100h-base-plus
Native training graph yes
Phase Kind Components Required inputs Loss keys
speech_recognition objective model — 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 patrickvonplaten/wavlm-libri-clean-100h-base-plus
Hugging Face ID patrickvonplaten/wavlm-libri-clean-100h-base-plus
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 cuda; verify checkpoint-specific requirements
Real-checkpoint evidence Release evidence; a registry default alone is not execution evidence
Implementation voicehub.models.asr_wavlm.modeling_asr_wavlm.WavLMForSpeechRecognition
Configuration voicehub.models.asr_wavlm.configuration_asr_wavlm.WavLMASRConfig
Source provenance No integration-specific bundled SOURCE.json is declared for this registry entry.
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

WavLMASRConfig

View source

WavLMASRConfig(**config_kwargs)

Parameters

  • **config_kwargs — Configuration fields validated by WavLMASRConfig.

Model

WavLMForSpeechRecognition

View source

AutoModelForSpeechRecognition.from_pretrained(
    pretrained_model_name_or_path,
    *,
    model_type='asr_wavlm',
    config=None,
    **model_kwargs,
)

Parameters

  • pretrained_model_name_or_path — Hub ID or compatible local directory.
  • model_type — Canonical model type; use 'asr_wavlm'.
  • config — Optional preloaded WavLMASRConfig instance.
  • **model_kwargs — Model-specific loading arguments.
from voicehub import get_model_spec

spec = get_model_spec('asr_wavlm')
print(spec.display_name, spec.task.value)
Purpose Public object
Discover get_model_spec('asr_wavlm')
Load and run AutoModelForSpeechRecognition
Configure WavLMASRConfig
Process AutoProcessor
Model implementation WavLMForSpeechRecognition
Normalized output ASROutput
Training contract get_training_spec('asr_wavlm')
Optimization lifecycle available_optimization_passes, apply_optimization_plan, optimization_manifest, restore_optimization_plan

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