facebook
/

unit_hifigan_HK_layer12.km2500_frame_TAT-TTS

Text-to-Speech Fairseq hk audio

Model card Files Files and versions Community

pipibjc commited on Oct 19, 2022

Commit

818f59d

•

1 Parent(s): 320ca90

Update README.md

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -10,8 +10,7 @@ language: hk
 ---
 ## unit_hifigan_HK_layer12.km2500_frame_TAT-TTS
-Speech-to-speech translation model from fairseq:
-- English-Hokkien
 - Trained with [TAT-TTS](https://sites.google.com/speech.ntut.edu.tw/fsw/home/tat-tts-corpus) data with 4 speakers in Taiwanese Hokkien accent. See [here]( https://research.facebook.com/publications/hokkien-direct-speech-to-speech-translation)
 for more training details.

 ---
 ## unit_hifigan_HK_layer12.km2500_frame_TAT-TTS
+Hokkien unit HiFiGAN based vocoder from fairseq:
 - Trained with [TAT-TTS](https://sites.google.com/speech.ntut.edu.tw/fsw/home/tat-tts-corpus) data with 4 speakers in Taiwanese Hokkien accent. See [here]( https://research.facebook.com/publications/hokkien-direct-speech-to-speech-translation)
 for more training details.