YuXiangLin

Questions about implementation

2

Hello, I try to reproduce your great work based on the github repo you mentioned before, but results seem to be not good. I'm new to object detection, so there...

What do the loss curves look like during your successful training?

5

Hello, I've attempted to train FAcodec using my own dataset. However, whether I start from scratch or fine-tune your provided checkpoint, the reconstructed audio clips are just noise. I fine-tuned...

What is the chinese phonemizer for pretrained multilinugual PL-BERT?

1

Hello, The model card says that the multilinugual PL-BERT https://huggingface.co/datasets/styletts2-community/multilingual-pl-bert is trained on this dataset: https://huggingface.co/datasets/styletts2-community/multilingual-phonemes-10k-alpha But I cannot find what package is used for chinese word phonemization. It's neither...

Hello, The statistics in the README.md for datasets v1.0 and v2.0 state that the testing set in v2.0 is five times larger than in v1.0; however, the file size appears...