Model reference · open weights
wavlm-libri-clean-100h-large is an open-weight audio or speech model from patrickvonplaten. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | patrickvonplaten |
|---|---|
| Type | Audio & music |
| Task | Speech→text |
| Runs with | transformers |
| Released | 2022-03-02 |
| Popularity | 12k downloads / month |
| Licence | Unknown |
About
This model is a fine-tuned version of microsoft/wavlm-large on the LIBRISPEECH_ASR - CLEAN dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.8069 | 0.34 | 300 | 0.7510 | 0.5809 |
| 0.2483 | 0.67 | 600 | 0.2023 | 0.1929 |
| 0.1033 | 1.01 | 900 | 0.1123 | 0.1028 |
| 0.0742 | 1.35 | 1200 | 0.0858 | 0.0771 |
| 0.057 | 1.68 | 1500 | 0.0722 | 0.0663 |
| 0.0421 | 2.02 | 1800 | 0.0682 | 0.0582 |
| 0.0839 | 2.35 | 2100 | 0.0630 | 0.0534 |
| 0.0307 | 2.69 | 2400 | 0.0603 | 0.0508 |
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys wavlm-libri-clean-100h-large for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wavlm-libri-clean-100h-large below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="wavlm-libri-clean-100h-large" -F file=@audio.mp3
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.