diarization - KeyError: 'embed.weight'

[RuslanSel]

I got the error running python diarization.py --config_path config/infer_est_nspk1.yaml --wav_path 0.wav --model_init WavLM-Large.pt
Traceback (most recent call last):
File "diarization.py", line 321, in
main(args)
File "diarization.py", line 272, in main
model_all_n_speakers = model_parameter_dict["embed.weight"].shape[0]
KeyError: 'embed.weight'

Thanks in advance.

[MarkWuNLP]

Hi, @RuslanSel , @czy97 will answer your question

[czy97]

I got the error running python diarization.py --config_path config/infer_est_nspk1.yaml --wav_path 0.wav --model_init WavLM-Large.pt Traceback (most recent call last): File "diarization.py", line 321, in main(args) File "diarization.py", line 272, in main model_all_n_speakers = model_parameter_dict["embed.weight"].shape[0] KeyError: 'embed.weight'

Thanks in advance.

Sorry for the late reply. Maybe you downloaded the model from the wrong url. We have saved the pre-trained model and the down-stream diarization model in the same checkpoint file. You should download the model from here: https://drive.google.com/file/d/16OwIyOk2uYm0aWtSPaS0S12xE8RxF7k_/view?usp=sharing, which is referenced in the result Table of https://github.com/microsoft/UniSpeech/tree/main/downstreams/speaker_diarization.

[RuslanSel]

Yes. I downloaded the model from the main README.md.
Thanks.

[luhuijun666]

I got the error running python diarization.py --config_path config/infer_est_nspk1.yaml --wav_path 0.wav --model_init WavLM-Large.pt Traceback (most recent call last): File "diarization.py", line 321, in main(args) File "diarization.py", line 272, in main model_all_n_speakers = model_parameter_dict["embed.weight"].shape[0] KeyError: 'embed.weight'
Thanks in advance.

Sorry for the late reply. Maybe you downloaded the model from the wrong url. We have saved the pre-trained model and the down-stream diarization model in the same checkpoint file. You should download the model from here: https://drive.google.com/file/d/16OwIyOk2uYm0aWtSPaS0S12xE8RxF7k_/view?usp=sharing, which is referenced in the result Table of https://github.com/microsoft/UniSpeech/tree/main/downstreams/speaker_diarization.

The url is missing~