Replies: 1 comment
-
|
Should be fixed in accf5c0 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hello all,
I tried to make use of whisper-diarization, but I don't get it to work. I recorded a meeting which is quite a big file and tried to analyze it. I used the command: python diarize.py -a "Test_meeting20241114.wav" --no-stem --whisper-model small --language en . I used the small model since I otherwise get the error that CUDA ran out of memory. It runs for a short time, but at a certain instant I get the following error:
File "..\whisper-diarization-main\diarize.py", line 163, in
audio_waveform.to(alignment_model.dtype).to(alignment_model.device),
AttributeError: 'numpy.ndarray' object has no attribute 'to'
It seems that nobody had this error yet since I couldn't find it in the discussions. How to solve this?
Beta Was this translation helpful? Give feedback.
All reactions