jeremy110
jeremy110
I might need some time to organize and then upload to GitHub. However, I won't be able to provide the BERT model and G2P parts, but you can still refer...
The G2P model was mainly written by other colleagues; I just used it. https://github.com/jeremy110/MeloTTS_hokkien If you see any SP symbols, you can ignore them. I was just experimenting with something...
Yes, I didn't modify the model part, only did data processing. I'm also not sure how their acoustic models are trained. If you want to work on three languages simultaneously,...
@UltramanSleepless It looks like you have modified the number of symbols. Please ensure that the number of symbols in your config.json matches the number of symbols in symbols.py used during...
是的，我是linux底下訓練的，因為我只想訓練自己的語言，所以有些韓文需要的包我都不安裝。 windows上我沒有測試過，建議還是在linux底下做訓練。
@KiON-GiON Yes, that’s right, it will download automatically.
@KiON-GiON Did you modify anything? I can’t quite remember if the checkpoint after training only contains the weight or if it includes other things as well. If it includes other...
MeloTTS doesn't support change voice style.
Did you modify data_utils.py to add your language labels? Also, 768 and 1024 are BERT embeddings and are related to your BERT model.
@TugdualKerjan Maybe you can refer to https://github.com/myshell-ai/MeloTTS/issues/160 https://github.com/myshell-ai/MeloTTS/issues/120