您尚未登录账户请先登录您的atyun账户，方可使用该功能
您的企业账号申请正在审核中审核通过后即可使用此功能，请耐心等待~
模型:
Yehor/wav2vec2-xls-r-300m-uk-with-small-lm
中文?? Join Ukrainian Speech Recognition Community - https://t.me/speech_recognition_uk
⭐ See other Ukrainian models - https://github.com/egorsmkv/speech-recognition-uk
This model has apostrophes and hyphens.
The language model is trained on the texts of the Common Voice dataset, which is used during training.
Metrics:
| Dataset | CER | WER |
|---|---|---|
| CV7 (no LM) | 0.0432 | 0.2288 |
| CV7 (with LM) | 0.0169 | 0.0706 |
| CV10 (no LM) | 0.0412 | 0.2206 |
| CV10 (with LM) | 0.0118 | 0.0463 |
More:
- The same model, but trained on noisy data: https://huggingface.co/Yehor/wav2vec2-xls-r-300m-uk-with-small-lm-noisy
- Traced JIT version: https://huggingface.co/Yehor/wav2vec2-xls-r-300m-uk-traced-jit