search

VinAIResearch / XPhoneBERT

XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech (INTERSPEECH 2023)
MIT License
306 stars 37 forks source link

Checkpoint request #22

Closed ndhuynh02 closed 1 week ago

ndhuynh02 commented 3 months ago

I am wanting to try out XPhoneBERT for my school project, but the main page README.md file doesn't clearly show how to generate audio from input text. I have try it out though, and I find that the model I am inferring through is RoBERTa, not XPhoneBERT. After that, I try looking for the infer code inference.py. Fortunately, it it is in the VITS_with_XPhoneBERT folder. In this code file, the model state reads from a checkpoint .pth file for inference. Therefore, I want to ask for this checkpoint so that I can use it for my school project. Thank you.

thelinhbkhn2014 commented 1 week ago

Thanks for your consideration, but sorry, following our company rules, I cannot release our TTS model