Clona Whisper small or medium modellproject
git clone https://huggingface.co/bjelkenhed/whisper-small-sv git clone https://huggingface.co/bjelkenhed/whisper-medium-sv
Install requirements
sudo add-apt-repository -y ppa:jonathonf/ffmpeg-4 sudo apt update sudo apt install -y ffmpeg sudo apt-get install git-lfs
Install python libraries
env_name=babelbox
python3 -m venv $env_name
source ~/$env_name/bin/activate
git clone https://github.com/huggingface/community-events.git
pip install -r community-events/whisper-fine-tuning-event/requirements.txt
python -c "import torch; print(torch.cuda.is_available())"
Log in to Huggingface
git config --global credential.helper store huggingface-cli login
Type your Huggingface access token
Create HF modell or clone existing
#huggingface-cli repo create whisper-small-sv
git clone https://huggingface.co/bjelkenhed/whisper-small-sv
git config --global user.email "bjelkenhed@gmail.com" git config --global user.name "Magnus Bjelkenhed"
tmux new -s mysession
tmux a -t mysession