Model reference · open weights
wav2vec2-large-english-phoneme is an open-weight audio or speech model from speech31. 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 | speech31 |
|---|---|
| Type | Audio & music |
| Task | Speech→text |
| Runs with | transformers |
| Released | 2022-09-17 |
| Popularity | 680 downloads / month |
| Licence | Open weights |
About
This model is a fine-tuned version of facebook/wav2vec2-large on the None 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 | Cer |
|---|---|---|---|---|
| 2.18 | 6.94 | 500 | 0.3118 | 0.0923 |
| 0.2622 | 13.88 | 1000 | 0.4387 | 0.1218 |
| 0.2145 | 20.83 | 1500 | 0.4441 | 0.1121 |
| 0.1429 | 27.77 | 2000 | 0.4001 | 0.1045 |
| 0.0927 | 34.72 | 2500 | 0.4692 | 0.1062 |
| 0.0598 | 41.66 | 3000 | 0.3960 | 0.0971 |
| 0.0356 | 48.61 | 3500 | 0.4069 | 0.0900 |
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys wav2vec2-large-english-phoneme for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-english-phoneme 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="wav2vec2-large-english-phoneme" -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.