CAiRE
/

wav2vec2-large-xlsr-53-cantonese

Automatic Speech Recognition

xlsr-fine-tuning-week

Inference Endpoints

Model card Files Files and versions Community

holylovenia commited on Jun 9, 2022

Commit

ba31dfa

•

1 Parent(s): 8a88000

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -33,7 +33,7 @@ model-index:
 Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Cantonese using the [Common Voice](https://huggingface.co/datasets/common_voice).
 When using this model, make sure that your speech input is sampled at 16kHz.
-The Common Voice `train` and `dev` were used for training.
 The script used for training can be found at [https://github.com/holylovenia/wav2vec2-pretraining](https://github.com/holylovenia/wav2vec2-pretraining).

 Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Cantonese using the [Common Voice](https://huggingface.co/datasets/common_voice).
 When using this model, make sure that your speech input is sampled at 16kHz.
+The Common Voice's validated `train` and `dev` were used for training.
 The script used for training can be found at [https://github.com/holylovenia/wav2vec2-pretraining](https://github.com/holylovenia/wav2vec2-pretraining).