Closed snowyu closed 2 years ago
Hey, this is not a bug. This is something related to the dataset and how tacotron works. If you want the model do be stable with small input, your data should have that.
Btw this works: tts --model_name tts_models/zh-CN/baker/tacotron2-DDC-GST --text "你好。"
@WeberJulian Thanks a lot, but why the half-width symbol "你好." doesn't work?
No idea sorry, I don't speak Chinese
@WeberJulian Then how to add these ".!?" chars to the stop words?
Not sure what you mean, sorry
@WeberJulian Then how to add these ".!?" chars to the stop words?
you can write your own text processor and preprocess the text before passing it to 🐸TTS. However, you need a bit of coding.
Describe the bug
Chinese text-to-speech sounds do not end correctly. There will be multiple incorrect tails at the end:
https://user-images.githubusercontent.com/327887/169764716-027dbff6-dc62-4d65-b5ce-38e45b85fb48.mov
To Reproduce
Expected behavior
https://user-images.githubusercontent.com/327887/169765160-a0f18ffc-c39c-499f-bf44-440a7145729f.mov
Logs
Environment
Additional context
No response