Model reference · open weights
wav2vec2-large-xlsr-53-dutch is an open-weight audio or speech model from jonatasgrosman, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Fine-tuned XLSR-53 large model for speech recognition in Dutch Fine-tuned facebook/wav2vec2-large-xlsr-53 on Dutch using the train and validation splits of Common Voice 6.1 and CSS10. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned thanks to the GPU credits generously given by the OVHcloud :) The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint Usage The model can be used directly (without a language model) as follows... Using the HuggingSound library: Writing your own inference script: Evaluation 1. To evaluate on mozilla-foundation/commonvoice60 with split test 2. To evaluate on speech-recognition-community-v2/devdata Citation If you want to cite this model you can use this:
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | jonatasgrosman |
|---|---|
| Type | Audio & music |
| Variants | 1 |
| Runs with | transformers |
| Released | 2022-03-02 |
| Popularity | 2.6M downloads / month |
| Likes | 17 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| wav2vec2-large-xlsr-53-dutch | — | BF16 | — | — | Weights ↗ |
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 nl | Test WER | 15.72 |
| Automatic Speech Recognition | Common Voice nl | Test CER | 5.35 |
| Automatic Speech Recognition | Common Voice nl | Test WER (+LM) | 12.84 |
| Automatic Speech Recognition | Common Voice nl | Test CER (+LM) | 4.64 |
| Automatic Speech Recognition | Robust Speech Event - Dev Data | Dev WER | 35.79 |
| Automatic Speech Recognition | Robust Speech Event - Dev Data | Dev CER | 17.67 |
| Automatic Speech Recognition | Robust Speech Event - Dev Data | Dev WER (+LM) | 31.54 |
| Automatic Speech Recognition | Robust Speech Event - Dev Data | Dev CER (+LM) | 16.37 |
Using it via the API
Once AxForge deploys wav2vec2-large-xlsr-53-dutch for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-xlsr-53-dutch 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-xlsr-53-dutch" -F file=@audio.mp3
Details
Languages
Trained / evaluated on
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗