ZhangXInFD / SpeechTokenizer

This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on
https://0nutation.github.io/SpeechTokenizer.github.io/
Apache License 2.0
466 stars 40 forks source link

Ask for number range of training loss. #15

Open liangpenglong opened 2 months ago

liangpenglong commented 2 months ago

I have a question about the final loss of training, could you tell me what is the approximate range of the size of the final loss when you train? About Gen loss , Mel Error, Q loss , Distill loss.