codec模型初始化部分参数无法正确初始化
Some weights of XCodec2Model were not initialized from the model checkpoint at HKUSTAudio/xcodec2 and are newly initialized: ['CodecEnc.conv_blocks.1.block.0.block.0.act.bias', 'CodecEnc.conv_blocks.1.block.0.block.2.act.bias', 'CodecEnc.conv_blocks.1.block.1.block.0.act.bias', 'CodecEnc.conv_blocks.1.block.1.block.2.act.bias', 'CodecEnc.conv_blocks.1.block.2.block.0.act.bias', 'CodecEnc.conv_blocks.1.block.2.block.2.act.bias', 'CodecEnc.conv_blocks.1.block.3.act.bias', 'CodecEnc.conv_blocks.2.block.0.block.0.act.bias', 'CodecEnc.conv_blocks.2.block.0.block.2.act.bias', 'CodecEnc.conv_blocks.2.block.1.block.0.act.bias', 'CodecEnc.conv_blocks.2.block.1.block.2.act.bias', 'CodecEnc.conv_blocks.2.block.2.block.0.act.bias', 'CodecEnc.conv_blocks.2.block.2.block.2.act.bias', 'CodecEnc.conv_blocks.2.block.3.act.bias', 'CodecEnc.conv_blocks.3.block.0.block.0.act.bias', 'CodecEnc.conv_blocks.3.block.0.block.2.act.bias', 'CodecEnc.conv_blocks.3.block.1.block.0.act.bias', 'CodecEnc.conv_blocks.3.block.1.block.2.act.bias', 'CodecEnc.conv_blocks.3.block.2.block.0.act.bias', 'CodecEnc.conv_blocks.3.block.2.block.2.act.bias', 'CodecEnc.conv_blocks.3.block.3.act.bias', 'CodecEnc.conv_blocks.4.block.0.block.0.act.bias', 'CodecEnc.conv_blocks.4.block.0.block.2.act.bias', 'CodecEnc.conv_blocks.4.block.1.block.0.act.bias', 'CodecEnc.conv_blocks.4.block.1.block.2.act.bias', 'CodecEnc.conv_blocks.4.block.2.block.0.act.bias', 'CodecEnc.conv_blocks.4.block.2.block.2.act.bias', 'CodecEnc.conv_blocks.4.block.3.act.bias', 'CodecEnc.conv_blocks.5.block.0.block.0.act.bias', 'CodecEnc.conv_blocks.5.block.0.block.2.act.bias', 'CodecEnc.conv_blocks.5.block.1.block.0.act.bias', 'CodecEnc.conv_blocks.5.block.1.block.2.act.bias', 'CodecEnc.conv_blocks.5.block.2.block.0.act.bias', 'CodecEnc.conv_blocks.5.block.2.block.2.act.bias', 'CodecEnc.conv_blocks.5.block.3.act.bias', 'CodecEnc.conv_final_block.0.act.bias']
Me to!!!I want to ask how to address this question?
Maybe you can try the original ckpts without pip install, https://github.com/zhenye234/X-Codec-2.0#setup
@ZhenYe234 @Qianguo The root cause is , the uploaded safetensors model does not match the codes, you have to initialized the model from pt file.
Morover, you have to rename your tensors to adapt to the model.
I have gave a neat solution to solve this problem quickly in https://huggingface.co/HKUSTAudio/xcodec2/discussions/13.
Later we will update Huggingface Model to make sure developers can use this huggingface model repo (not pt file repo) in the huggingface style. Thank you for your attention.