_pickle.UnpicklingError: invalid load key, '\x08'.

[Zomun]

(sd) root@novo:~/pyannote-audio-develop# python seg.py CUDA is available. torchvision is not available - cannot save figures Traceback (most recent call last): File "/root/pyannote-audio-develop/seg.py", line 28, in pipeline = Pipeline.from_pretrained("/root/pyannote-audio-develop/pyannote-sg/local/config.yaml") File "/root/anaconda3/envs/sd/lib/python3.10/site-packages/pyannote/audio/core/pipeline.py", line 137, in from_pretrained pipeline = Klass(params) File "/root/anaconda3/envs/sd/lib/python3.10/site-packages/pyannote/audio/pipelines/speaker_diarization.py", line 166, in init self._embedding = PretrainedSpeakerEmbedding( File "/root/anaconda3/envs/sd/lib/python3.10/site-packages/pyannote/audio/pipelines/speaker_verification.py", line 745, in PretrainedSpeakerEmbedding return PyannoteAudioPretrainedSpeakerEmbedding( File "/root/anaconda3/envs/sd/lib/python3.10/site-packages/pyannote/audio/pipelines/speakerverification.py", line 651, in init self.model: Model = get_model(self.embedding, use_auth_token=use_auth_token) File "/root/anaconda3/envs/sd/lib/python3.10/site-packages/pyannote/audio/pipelines/utils/getter.py", line 75, in get_model model = Model.from_pretrained( File "/root/anaconda3/envs/sd/lib/python3.10/site-packages/pyannote/audio/core/model.py", line 671, in from_pretrained loaded_checkpoint = pl_load(path_for_pl, map_location=map_location) File "/root/anaconda3/envs/sd/lib/python3.10/site-packages/lightning_fabric/utilities/cloud_io.py", line 57, in _load return torch.load(f, map_location=map_location) # type: ignore[arg-type] File "/root/anaconda3/envs/sd/lib/python3.10/site-packages/torch/serialization.py", line 1040, in load return _legacy_load(opened_file, map_location, pickle_module, pickle_load_args) File "/root/anaconda3/envs/sd/lib/python3.10/site-packages/torch/serialization.py", line 1262, in _legacy_load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, '\x08'. seg.py : pipeline = Pipeline.from_pretrained("/root/pyannote-audio-develop/pyannote-sg/local/config.yaml")

pipeline = Pipeline.from_pretrained("pyannote/speaker-diarization", use_auth_token="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")

将 pipeline 移动到 GPU 上（如果有 GPU）

pipeline.to(device)

config.yaml: version: 3.1.0

pipeline: name: pyannote.audio.pipelines.SpeakerDiarization params: clustering: AgglomerativeClustering embedding: /root/pyannote-audio-develop/pyannote-sg/local/wespeaker-voxceleb-resnet34-LM/speaker-embedding.onnx embedding_batch_size: 32 embedding_exclude_overlap: true segmentation: /root/pyannote-audio-develop/pyannote-sg/local/pytorch_model.bin # https://huggingface.co/pyannote/segmentation-3.0/tree/main segmentation_batch_size: 32

params: clustering: method: centroid min_cluster_size: 12 threshold: 0.7045654963945799 segmentation: min_duration_off: 0.0

[B1SH0PP]

_pickle.UnpicklingError: invalid load key, '\x08'. Did you solve this problem, bro? @Zomun