training pause "Processed dataset to: ./training/mo/ Missing dataset: ./training/mo//whisper.json

JarodMica / ai-voice-cloning

GNU General Public License v3.0

656 stars 144 forks source link

training pause "Processed dataset to: ./training/mo/ Missing dataset: ./training/mo//whisper.json #67

Open Alexbabylon opened 8 months ago

Alexbabylon commented 8 months ago

2024-03-23_6-57-10

can some help please with this issue ?

thanks

StoyanNakov commented 8 months ago

here is same

Sli7e commented 7 months ago

I had the same problem and could fix it like mentioned here: https://github.com/openai/whisper/discussions/1468 I had to install ffmpeg in the virtual enviroment(venv) created by the .bat files. I edited the start.bat and the activate.bat to get a cmd in the right enviroment.

start.bat:

Line 4: python .\src\main.py %*
to
Line 4: rem python .\src\main.py %*

activate.bat add:

Line 30: cmd /k

Start the start.bat

In the terminal run: conda install -c conda-forge ffmpeg