This is the code for the SpeechTokenizer presented in the SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models. Samples are presented on
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.
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.