search

TensorSpeech / TensorFlowTTS

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)
https://tensorspeech.github.io/TensorFlowTTS/
Apache License 2.0
3.8k stars 810 forks source link

Does the number of chars in char set (processor) impacts the speed of learning. #750

Closed abaddon-moriarty closed 2 years ago

abaddon-moriarty commented 2 years ago

Hi,

I was wondering how the size of the character set in the processor impacts the learning of the model. Would for example have a processor being able to handle most western European languages - so with all normal alphabet chars as well as special chars in each language - train slower ?

This would include all the accented character, in French, German, Czech, Slovak, as well as From countries from Northern Europe. The char list would get pretty long and I'm afraid it's going to slow training.

Has anybody trained with a recognisably long char set or know more details about how it would affect the model ?

Thanks

stale[bot] commented 2 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.