Closed fengyunzaidushi closed 12 months ago
class DiarizationPipeline:
def __init__(
self,
model_name='pyannote/speaker-diarization@2.1',
use_auth_token=None,
device: Optional[Union[str, torch.device]] = 'cpu',
):
if isinstance(device, str):
device = torch.device(device)
print(f'model_name is {model_name}')
self.model = Pipeline.from_pretrained(model_name, use_auth_token=use_auth_token).to(device)
i think the issue is which version of pyannote.audio should be installed
Have you visited speaker-diarization, segmentation and accepted user conditions?
Have you visited speaker-diarization, segmentation and accepted user conditions?您是否访问过扬声器分类、细分和接受的用户条件?
yes,i have accepted yet.
I'll check this out. Thank you for this issue.
@fengyunzaidushi could you please send the versions of the installed packages?
pip list
I have already met this error. In my case, it occurred in two cases:
@fengyunzaidushi check out new install.sh script.
i find the same issue feat: send pipeline to device with Pipeline.to(device)