search

HenestrosaDev / audiotext

A desktop application that transcribes audio from files, microphone input or YouTube videos with the option to translate the content and create subtitles.
Other
112 stars 10 forks source link

CUDA error when CPU selected #12

Closed wimj888 closed 6 months ago

wimj888 commented 6 months ago

Steps to reproduce

I got a CUDA error on several retries to transcribe an English mp3 file of about 4 MB on Windows 11. Version of audiotext used was 2.1.0

Expected behaviour

Transcribed text of audio file

Actual behaviour

Traceback (most recent call last): File "controller\main_controller.py", line 170, in _transcribe_using_whisperx File "whisperx\asr.py", line 287, in load_model model = model or WhisperModel(whisper_arch, File "faster_whisper\transcribe.py", line 130, in init RuntimeError: CUDA failed with error CUDA driver version is insufficient for CUDA runtime version

image

wimj888 commented 6 months ago

As this might be related to the ffmpeg install, following is the output on my system :

image

I got around it by editing the config.ini and settting use_cpu = True For some reason this is not done via the GUI.

HenestrosaDev commented 6 months ago

Thanks for the detailed information. I'll take a look at this tomorrow as it seems to be related to the logic that handles changing the value of the "Use CPU" checkbox.

HenestrosaDev commented 6 months ago

As this might be related to the ffmpeg install, following is the output on my system :

image

I got around it by editing the config.ini and settting use_cpu = True For some reason this is not done via the GUI.

I've checked this and it seems to be working fine. The config value is updated correctly according to the checkbox value.