search

SuyashMore / MevonAI-Speech-Emotion-Recognition

Identify the emotion of multiple speakers in an Audio Segment
https://colab.research.google.com/github/SuyashMore/MevonAI-Speech-Emotion-Recognition/blob/master/src/notebooks/Emotion_Recognition_Demo.ipynb
MIT License
165 stars 46 forks source link

error for adding audio folder #7

Closed har790 closed 3 years ago

har790 commented 3 years ago

hey there, I tried a lot to add audio folder but it throws error, even I made one folder for one file and changed the code but still its shows error
as such :- Traceback (most recent call last): File "speechEmotionRecognition.py", line 62, in bk.diarizeFromFolder(f'{INPUT_FOLDER_PATH}{subdir}{"/"}',(f'{OUTPUT_FOLDER_PATH}{subdir}{"/"}')) File "/content/emotion/src/bulkDiarize.py", line 29, in diarizeFromFolder diarizeAudio(TOTAL_PATH,TOTAL_OUTPUT_PATH,expectedSpeakers=2) File "/content/emotion/src/speakerDiarization.py", line 242, in diarizeAudio main("filterTemp.wav", embedding_per_second=0.6, overlap_rate=0.4,exportFile=exportFile,expectedSpeakers=expectedSpeakers) File "/content/emotion/src/speakerDiarization.py", line 170, in main feats = np.array(feats)[:,0,:].astype(float) # [splits, embedding dim] IndexError: too many indices for array: array is 1-dimensional, but 3 were indexed

please could u explain me .

SuyashMore commented 3 years ago

Check this out #2