josephwong14wkh

I am currently training whisper with large-v2 size using pipeline training with 2 gpus. I have my own custom dataset and i pass it to deepspeed for pipeline training. However,...

Do you know how to use TiedLayerSpec? I want to finetune whisper large v2 using multiple GPU (single node). Embedding layer is used before the transformer decoder and after the...

[Help]: Questions about the tokenizers of vevo1.5

9

Thank you for your great works! I am now working on audio-to-audio voice conversion and there are two questions regarding vevo1.5. 1. I would like to train a content tokenizer...

[Seed-vc-v2] Training script of the VQ model in v2

1

Hi, thank you for the great work. I saw into the code and realized that we are not able to train / finetune the VQ in the model. As i...