svlqd
3d48f473b0
- found problems with mps - integrated jinja2 templates for rendering (.tex?) - raw ui & bad structure
Notecast
Notecast is a simple and minimalistic utilite to transcribe audiofiles to text and create a conspect.
Requires nvidia cuda toolkit v12.4
You can create environment running
conda env create -f environment.yml
or for CUDA/Nvidia:
conda create -n notecast -c pytorch -c nvidia pytorch torchvision torchaudio transformers python=3.12
conda install ffmpeg customtkinter openai -c conda-forge -c bioconda