NTQAI
/

wav2vec2-large-japanese

Automatic Speech Recognition Transformers PyTorch JAX

Japanese wav2vec2 audio speech Eval Results Inference Endpoints

Model card Files Files and versions Community

nhanv commited on Feb 17, 2023

Commit

f4feb98

•

1 Parent(s): cce8617

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -29,7 +29,7 @@ model-index:
          value: 21.9
 ---
 # Wav2Vec2-Large-Japanese
-Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Japanese using the [Common Voice](https://huggingface.co/datasets/common_voice), [JSUT](https://sites.google.com/site/shinnosuketakamichi/publication/jsut), [TEDxJP](https://github.com/laboroai/TEDxJP-10K) and some other data. This model is a model trained on public data. If you want to use trained model with more 600 hours of data and higher accuracy please contact nha.nguyen@ntq-solution.com.vn
 When using this model, make sure that your speech input is sampled at 16kHz.

          value: 21.9
 ---
 # Wav2Vec2-Large-Japanese
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Japanese using the [Common Voice](https://huggingface.co/datasets/common_voice), [JSUT](https://sites.google.com/site/shinnosuketakamichi/publication/jsut), [TEDxJP](https://github.com/laboroai/TEDxJP-10K) and some other data. This model is a model trained on public data. If you want to use trained model with more 600 hours of data and higher accuracy please contact nha282@gmail.com
 When using this model, make sure that your speech input is sampled at 16kHz.