Nice work! But how to deal with the following error?

[xuduo18311199384]

Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.0.0.weight, /home/zgdx/.cache/modelscope/hub/iic/emotion2vec_base_finetuned/emotion2vec_base.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.0.0.bias, /home/zgdx/.cache/modelscope/hub/iic/emotion2vec_base_finetuned/emotion2vec_base.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.1.0.weight, /home/zgdx/.cache/modelscope/hub/iic/emotion2vec_base_finetuned/emotion2vec_base.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.1.0.bias, /home/zgdx/.cache/modelscope/hub/iic/emotion2vec_base_finetuned/emotion2vec_base.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.2.0.weight, /home/zgdx/.cache/modelscope/hub/iic/emotion2vec_base_finetuned/emotion2vec_base.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.2.0.bias, /home/zgdx/.cache/modelscope/hub/iic/emotion2vec_base_finetuned/emotion2vec_base.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.3.0.weight, /home/zgdx/.cache/modelscope/hub/iic/emotion2vec_base_finetuned/emotion2vec_base.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.3.0.bias, /home/zgdx/.cache/modelscope/hub/iic/emotion2vec_base_finetuned/emotion2vec_base.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.proj.weight, /home/zgdx/.cache/modelscope/hub/iic/emotion2vec_base_finetuned/emotion2vec_base.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.proj.bias, /home/zgdx/.cache/modelscope/hub/iic/emotion2vec_base_finetuned/emotion2vec_base.pt
unfreezing only the first 6 transformer blocks
/home/zgdx/.conda/envs/deeptalk/lib/python3.9/site-packages/huggingface_hub/file_download.py:795: FutureWarning: resume_download is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use force_download=True.
warnings.warn(
Traceback (most recent call last):
File "/home/zgdx/.conda/envs/deeptalk/lib/python3.9/site-packages/urllib3/connection.py", line 198, in _new_conn
sock = connection.create_connection(
File "/home/zgdx/.conda/envs/deeptalk/lib/python3.9/site-packages/urllib3/util/connection.py", line 85, in create_connection
raise err
File "/home/zgdx/.conda/envs/deeptalk/lib/python3.9/site-packages/urllib3/util/connection.py", line 73, in create_connection
sock.connect(sa)
OSError: [Errno 101] Network is unreachable

[whwjdqls]

It seems like a network problem. I don't think its the problem with the code.

[xuduo18311199384]

Is this sentence normal? "Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.3.0.weight, /home/zgdx/.cache/modelscope/hub/iic/emotion2vec_base_finetuned/emotion2vec_base.pt“

[whwjdqls]

Yup. The backbone we are using is from emotion2vec, which uses the data2vec2 architecture. Data2vec2 consists of a transformer encoder and a CNN decoder, but as Data2vec2 is used as a feature extractor, the decoder is unused. We can just disregard it as we don't use it anyway.

Feel free to ask any more questions :)