Model reference · open weights
wav2vec2-large-xlsr-53-chinese-zh-cn 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 Chinese Fine-tuned facebook/wav2vec2-large-xlsr-53 on Chinese using the train and validation splits of Common Voice 6.1, CSS10 and ST-CMDS. 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 The model can be evaluated as follows on the Chinese (zh-CN) test data of Common Voice. Test Result: In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the evaluation script described above on other models as well (on 2021-05-13). Note that the table below may show different results from those already reported, this may have been caused due to some specificity of the other evaluation scripts used. 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 | 1.3M downloads / month |
| Likes | 135 |
| 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-chinese-zh-cn | — | BF16 | — | — | Weights ↗ |
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Speech Recognition | Common Voice zh-CN | Test WER | 82.37 |
| Speech Recognition | Common Voice zh-CN | Test CER | 19.03 |
Using it via the API
Once AxForge deploys wav2vec2-large-xlsr-53-chinese-zh-cn for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-xlsr-53-chinese-zh-cn 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-chinese-zh-cn" -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 ↗