search

pyannote / pyannote-audio

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
http://pyannote.github.io
MIT License
6.38k stars 784 forks source link

issue in using pretrained models #152

Closed rohithkodali closed 5 years ago

rohithkodali commented 5 years ago

hi i have been following the pretrained models tutorial but i have an issue with loading the models. it says

SAD_MODEL = (/pyannote/pyannote-audio/tutorials/models/speech_activity_detection/train/' 'AMI.SpeakerDiarization.MixHeadset.train/weights/0280.pt') File "/home/rohit/PycharmProjects/pyannote/temp.py", line 31, in sad = SequenceLabeling(model=SAD_MODEL,feature_extraction=mfcc_extractor) File "/home/rohit/anaconda3/envs/pyannote/lib/python3.6/site-packages/pyannote/audio/labeling/extraction.py", line 76, in init self.model = model.eval().to(self.device) AttributeError: 'str' object has no attribute 'eval'

is there any way to load the model or am i doing something wrong in loading

hbredin commented 5 years ago

I think this is the same issue as #151 . You need to use the develop branch of pyannote.audio.