search

ylacombe / finetune-hf-vits

Finetune VITS and MMS using HuggingFace's tools
MIT License
124 stars 31 forks source link

Cannot load model checkpoints #2

Open MobeenHameed1 opened 11 months ago

MobeenHameed1 commented 11 months ago

After training the mms-tts-urd_arabic-script on custom data, the final model is used for inference and works. However, the new model is not able to pronounce the words well. I thought it might be because the model is overfitted so wanted to load inference from the model checkpoints. However, it throws error with the standard huggingface pipeline code, specifically the absence of the config.json etc. On copying the last model files into the checkpoint directory the inference code works and generates an output .wav file but the file is blank with no audio. I am using the inference code provided by dunkerbunker in issue#1

ylacombe commented 11 months ago

Hi @MobeenHameed1, can you send the inference code that you use ?

muhammadsaadgondal commented 3 months ago

@MobeenHameed1 did you get your problem solved?

Waitday commented 1 month ago

i hame the same problem。did you get your problem solved? @muhammadsaadgondal