Model reference · open weights
wav2vec2-cv-be is an open-weight audio or speech model from ales. 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 | ales |
|---|---|
| Type | Audio & music |
| Task | Speech→text |
| Runs with | transformers |
| Released | 2022-04-13 |
| Popularity | 191k downloads / month |
| Licence | Open, with conditions |
About
Fine-tuned version of facebook/wav2vec2-base on mozilla-foundation/common_voice_8_0 be dataset.
Train, Dev, Test splits were used as they are present in the dataset. No additional data was used from Validated split,
only 1 voicing of each sentence was used - the way the data was split by CommonVoice CorporaCreator.
To build a better model one can use additional voicings from Validated split for sentences already present in Train, Dev, Test splits,
i.e. enlarge mentioned splits.
Language model was built using KenLM.
5-gram Language model was built on sentences from Train + (Other - Dev - Test) splits of mozilla-foundation/common_voice_8_0 be dataset.
Source code is available here.
This page contains interactive demo widget that lets you test this model right in a browser.
However, this widget uses Acoustic model only without Language model that significantly improves overall performance.
You can play with full pipeline of Acoustic model + Language model on the following spaces page (also works from browser).
From the published model card. Full card on the HuggingFace links in the sidebar.
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Automatic Speech Recognition | Common Voice 8 | Dev WER | 17.610 |
| Automatic Speech Recognition | Common Voice 8 | Test WER | 18.700 |
| Automatic Speech Recognition | Common Voice 8 | Dev WER (with LM) | 11.500 |
| Automatic Speech Recognition | Common Voice 8 | Test WER (with LM) | 12.400 |
Using it via the API
Once AxForge deploys wav2vec2-cv-be for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-cv-be 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-cv-be" -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.