exp_w2v2t_ru_wavlm_s363
Fine-tuned microsoft/wavlm-large for speech recognition using the train split of Common Voice 7.0 (ru). When using this model, make sure that your speech input is sampled at 16kHz.
This model has been fine-tuned by the HuggingSound tool.
- Downloads last month
- 280
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support