mio
/

Text-to-Speech
ESPnet
jp
audio

Suggestions on how to train a personal model using ESPnet

#1
by Edu4000 - opened

Hello, I was lookig at your fine-tuned model and wanted to say it is impresive. I am a beginner in HuggingFace and wanted to ask for help in doing something similar to what you did. I was lookig at ESPnet's repo on GitHub and have already done the recipe, but I am having trouble understanding the next steps with the bash scripts . I would gladly take any advice 😁

Sign up or log in to comment