Model reference · open weights
wav2vec2-large-xlsr-53-polish 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 Polish Fine-tuned facebook/wav2vec2-large-xlsr-53 on Polish using the train and validation splits of Common Voice 6.1. 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 | 3.1M downloads / month |
| Likes | 12 |
| 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-polish | — | 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 pl | Test WER | 14.21 |
| Automatic Speech Recognition | Common Voice pl | Test CER | 3.49 |
| Automatic Speech Recognition | Common Voice pl | Test WER (+LM) | 10.98 |
| Automatic Speech Recognition | Common Voice pl | Test CER (+LM) | 2.93 |
| Automatic Speech Recognition | Robust Speech Event - Dev Data | Dev WER | 33.18 |
| Automatic Speech Recognition | Robust Speech Event - Dev Data | Dev CER | 15.92 |
| Automatic Speech Recognition | Robust Speech Event - Dev Data | Dev WER (+LM) | 29.31 |
| Automatic Speech Recognition | Robust Speech Event - Dev Data | Dev CER (+LM) | 15.17 |
Using it via the API
Once AxForge deploys wav2vec2-large-xlsr-53-polish for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-xlsr-53-polish 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-polish" -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 ↗