Model reference · open weights
wav2vec2-xls-r-cs-250 is an open-weight audio or speech model from comodoro, 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
Czech wav2vec2-xls-r-300m-cs-250 This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the commonvoice 8.0 dataset as well as other datasets listed below. It achieves the following results on the evaluation set: - Loss: 0.1271 - Wer: 0.1475 - Cer: 0.0329 The eval.py script results using a LM are: - WER: 0.07274312090176113 - CER: 0.021207369275558875 Model description Fine-tuned facebook/wav2vec2-large-xlsr-53 on Czech using the Common Voice dataset. When using this model, make sure that your speech input is sampled at 16kHz. The model can be used directly (without a language model) as follows: Evaluation The model can be evaluated using the attached eval.py script: Training and evaluation data The Common Voice 8.0 train and validation datasets were used for training, as well as the following datasets: - Šmídl, Luboš and Pražák, Aleš, 2013, OVM – Otázky Václava Moravce, LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL), Faculty of Mathematics and Physics, Charles University, http://hdl.handle.net/11858/00-097C-0000-000D-EC98-3. - Pražák, Aleš and Šmídl, Luboš, 2012, Czech Parliament Meetings, LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL), Faculty of Mathematics and Physics, Charles University, http://hdl.handle.net/11858/00-097C-0000-0005-CF9C-4. - Plátek, Ondřej; Dušek, Ondřej and Jurčíček, Filip, 2016, Vystadial 2016 – Czech data, LINDAT/CLARIAH-CZ digital library at the Institute of Formal and Applied Linguistics (ÚFAL), Faculty of Mathematics and Physics, Charles University, http://hdl.handle.net/11234/1-1740. Training hyperparameters The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 32 - evalbatchsize: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lrschedulertype: linear - lrschedulerwarmupsteps: 800 - numepochs: 5 - mixedprecisiontraining: Native AMP Training results Framework versions - Transformers 4.16.2 - Pytorch 1.10.1+cu102 - Datasets 1.18.3 - Tokenizers 0.11.0
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | comodoro |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 315M |
| Variants | 1 |
| Runs with | transformers |
| Based on | facebook/wav2vec2-xls-r-300m |
| Released | 2022-03-02 |
| Popularity | 1.6M downloads / month |
| Likes | 3 |
| 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-xls-r-300m-cs-250 | 315M | BF16 | ~0.7 GB | ✓ | 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 8 | Test WER | 7.3 |
| Automatic Speech Recognition | Common Voice 8 | Test CER | 2.1 |
| Automatic Speech Recognition | Robust Speech Event - Dev Data | Test WER | 43.44 |
| Automatic Speech Recognition | Robust Speech Event - Test Data | Test WER | 38.5 |
Using it via the API
Once AxForge deploys wav2vec2-xls-r-cs-250 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-xls-r-cs-250 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-xls-r-cs-250" -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 ↗