-
-
Notifications
You must be signed in to change notification settings - Fork 758
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
SpeakerDiarization in offline mode can't work #1554
Comments
Thank you for your issue.You might want to check the FAQ if you haven't done so already. Feel free to close this issue if you found an answer in the FAQ. If your issue is a feature request, please read this first and update your request accordingly, if needed. If your issue is a bug report, please provide a minimum reproducible example as a link to a self-contained Google Colab notebook containing everthing needed to reproduce the bug:
Providing an MRE will increase your chance of getting an answer from the community (either maintainers or other power users). Companies relying on
|
Solved... It was a path issue. |
Hello, I also encountered the same issue. May I ask how you resolved it? |
请问你是怎么解决的 |
你解决了这个问题吗 |
还需要修改哪里的路径呢 |
When I use the SpeakerDiarization feature offline, I find that version 3.1 runs very slowly, and there are frequent memory errors. Thus, I am considering switching to the 2.0 yaml. However, during use, I noticed that the directory structure is quite different from 3.0. I have already referred to issues #1427 and #1294, but I still encounter errors. Could you help me identify the problem?
directory:
D:\Code\models\pyannote\config.yaml
D:\Code\models\pyannote\models--pyannote--segmentation
D:\Code\models\pyannote\speechbrain\spkrec-ecapa-voxceleb
D:\Code\models\pyannote\config.yaml
pipeline:
name: pyannote.audio.pipelines.SpeakerDiarization
params:
clustering: AgglomerativeClustering
embedding: D:/Code/models/pyannote2/speechbrain/spkrec-ecapa-voxceleb
embedding_batch_size: 32
embedding_exclude_overlap: true
segmentation: D:/Code/models/pyannote2/models--pyannote--segmentation/pytorch_model.bin
segmentation_batch_size: 32
D:\Code\models\pyannote\speechbrain\spkrec-ecapa-voxceleb\hyperparams.yaml
#Pretrain folder (HuggingFace)
pretrained_path: D:/Code/models/pyannote2/speechbrain/spkrec-ecapa-voxceleb
error
File "D:\conda_env\envs\py\lib\site-packages\pyannote\audio\core\pipeline.py", line 136, in from_pretrained
pipeline = Klass(**params)
File "D:\conda_env\envs\py\lib\site-packages\pyannote\audio\pipelines\speaker_diarization.py", line 169, in init
self.embedding = PretrainedSpeakerEmbedding(
File "D:\conda_env\envs\py\lib\site-packages\pyannote\audio\pipelines\speaker_verification.py", line 749, in PretrainedSpeakerEmbedding
return PyannoteAudioPretrainedSpeakerEmbedding(
File "D:\conda_env\envs\py\lib\site-packages\pyannote\audio\pipelines\speaker_verification.py", line 655, in init
self.model: Model = get_model(self.embedding, use_auth_token=use_auth_token)
File "D:\conda_env\envs\py\lib\site-packages\pyannote\audio\pipelines\utils\getter.py", line 75, in get_model
model = Model.from_pretrained(
File "D:\conda_env\envs\py\lib\site-packages\pyannote\audio\core\model.py", line 624, in from_pretrained
path_for_pl = hf_hub_download(
File "D:\conda_env\envs\py\lib\site-packages\huggingface_hub\utils_validators.py", line 110, in _inner_fn
validate_repo_id(arg_value)
File "D:\conda_env\envs\py\lib\site-packages\huggingface_hub\utils_validators.py", line 158, in validate_repo_id
raise HFValidationError(
huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': 'D:/Code/models/pyannote2/speechbrain/spkrec-ecapa-voxceleb'. Use
repo_type
argument if needed.The text was updated successfully, but these errors were encountered: