search

SevaSk / ecoute

Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox. It also generates a suggested response using OpenAI's GPT-3.5 for the user to say based on the live transcription of the conversation.
https://github.com/SevaSk/ecoute
MIT License
5.89k stars 827 forks source link

Torch library dependent file issue #180

Open Abhisheknakka opened 6 months ago

Abhisheknakka commented 6 months ago

issue with fbgeem dependent file in torch library issue.

import torch Traceback (most recent call last): File "<pyshell#0>", line 1, in import torch File "C:\Users\nsnai\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch__init__.py", line 141, in raise err OSError: [WinError 126] The specified module could not be found. Error loading "C:\Users\nsnai\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\lib\fbgemm.dll" or one of its dependencies. Capture

ossamamahjour commented 3 months ago

@Abhisheknakka did you get any news answers regarding this issue

waldyd commented 3 months ago

Modifying requirements.txt worked for me:

numpy==1.24.3
openai-whisper==20230314
Wave==0.0.2
openai==0.27.6
customtkinter==5.1.3
PyAudioWPatch==0.2.12.5
--extra-index-url https://download.pytorch.org/whl/cu117
torch==2.3.1

[1] https://stackoverflow.com/questions/78114412/import-torch-how-to-fix-oserror-winerror-126-error-loading-fbgemm-dll-or-depen