Hello！
Thank you very much for your work！
When I use iic/emotion2vec_plus_base to extract emotion2vec embeddings, the following error occurs:
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.0.0.weight, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.0.0.bias, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.1.0.weight, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.1.0.bias, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.2.0.weight, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.2.0.bias, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.3.0.weight, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.3.0.bias, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.proj.weight, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.proj.bias, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
2025-10-23 16:39:21,339 - modelscope - WARNING - No preprocessor field found in cfg.
2025-10-23 16:39:21,339 - modelscope - WARNING - No val key and type key found in preprocessor domain of configuration.json file.
2025-10-23 16:39:21,339 - modelscope - WARNING - Cannot find available config to build preprocessor at mode inference, current config: {'model_dir': '/home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base'}. trying to build by task and model information.
2025-10-23 16:39:21,339 - modelscope - INFO - No preprocessor key ('funasr', 'emotion-recognition') found in PREPROCESSOR_MAP, skip building preprocessor. If the pipeline runs normally, please ignore this log.
Processing WAV files: 0%| | 0/17500 [00:00<?, ?it/sError processing 0016_001569.wav: 'str' object has no attribute 'to' | 0/1 [00:00<?, ?it/s]
0%| | 0/1 [00:02<?, ?it/s]
I don't know why this problem occurs. Could you please help me solve this problem? Can you provide specific versions of funasr and modelscope？
Hello！
Thank you very much for your work！
When I use iic/emotion2vec_plus_base to extract emotion2vec embeddings, the following error occurs:
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.0.0.weight, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.0.0.bias, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.1.0.weight, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.1.0.bias, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.2.0.weight, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.2.0.bias, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.3.0.weight, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.blocks.3.0.bias, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.proj.weight, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
Warning, miss key in ckpt: modality_encoders.AUDIO.decoder.proj.bias, /home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base/model.pt
2025-10-23 16:39:21,339 - modelscope - WARNING - No preprocessor field found in cfg.
2025-10-23 16:39:21,339 - modelscope - WARNING - No val key and type key found in preprocessor domain of configuration.json file.
2025-10-23 16:39:21,339 - modelscope - WARNING - Cannot find available config to build preprocessor at mode inference, current config: {'model_dir': '/home/xsy/.cache/modelscope/hub/models/iic/emotion2vec_plus_base'}. trying to build by task and model information.
2025-10-23 16:39:21,339 - modelscope - INFO - No preprocessor key ('funasr', 'emotion-recognition') found in PREPROCESSOR_MAP, skip building preprocessor. If the pipeline runs normally, please ignore this log.
Processing WAV files: 0%| | 0/17500 [00:00<?, ?it/sError processing 0016_001569.wav: 'str' object has no attribute 'to' | 0/1 [00:00<?, ?it/s]
0%| | 0/1 [00:02<?, ?it/s]
I don't know why this problem occurs. Could you please help me solve this problem? Can you provide specific versions of funasr and modelscope？