asr_wavlm model guide¶
Overview¶
asr_wavlm is a VoiceHub automatic speech recognition
integration. This page is generated from the model registry and its executable
data and training contracts, so the documented support stays aligned with code. Open the asr_wavlm Colab notebook.
Quickstart¶
- Install VoiceHub and the provider extra shown above.
- Choose a checkpoint that matches this integration.
- Place a supported recording at
speech.wav. - Transcribe it and inspect both the full text and timed segments.
from voicehub import AutoModelForSpeechRecognition
model = AutoModelForSpeechRecognition.from_pretrained(
'patrickvonplaten/wavlm-libri-clean-100h-base-plus',
model_type='asr_wavlm',
device="cuda",
lazy_load=True,
)
output = model.transcribe("speech.wav")
print(output.text)
for segment in output.segments:
print(segment.start, segment.end, segment.text)
Use only authorized recordings for reference voice, transcription, detection, or evaluation. The example selects a concrete device; verify checkpoint-specific hardware needs and pin an immutable revision before production use.
Supported tasks and capabilities¶
| Property | Value |
|---|---|
| Task | Automatic speech recognition |
| Architecture | wavlm |
| Runtime | VoiceHub-native |
| Capabilities | automatic-speech-recognition, timestamps, safetensors, fine-tuning, voicehub-native |
| Reusable components | — |
Data 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. Follow the shared data workflow for manifest loading, audio validation, leakage-safe splits, and model-owned preprocessing.
Checkpoints, provenance, and license¶
| Property | Value |
|---|---|
| Default checkpoint | patrickvonplaten/wavlm-libri-clean-100h-base-plus |
| Checkpoint status | Registry default; pin an immutable revision for production and reproducible 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.
The default checkpoint identifies the expected family, not every compatible variant. Confirm the selected checkpoint's revision, access terms, provenance, and license before downloading or redistributing it.
Optimization and training support¶
All public optimizations enter this model through the shared
BaseSpeechModel lifecycle. Use available_optimization_passes() to discover
the public pass registry, then apply, inspect, serialize, or restore a plan
through the common model API. Application remains fail-closed when the active
runtime or hardware cannot satisfy a pass.
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() before constructing a
trainer. Follow the shared training workflow for a
one-step smoke test, validation, checkpoint resume, optimization, and portable
export.
Public API¶
| Purpose | Public object |
|---|---|
| Discover | get_model_spec('asr_wavlm') |
| Load and run | AutoModelForSpeechRecognition |
| Configure | WavLMASRConfig |
| 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 |
Related shared documentation: