20 lines
586 B
Markdown
20 lines
586 B
Markdown
|
|
# Purpose
|
|
speech to text command line utility by leveraging off ollama a local speech-to-text model
|
|
|
|
## Setup
|
|
|
|
```bash
|
|
# Create the environment with Python 3.10 and CUDA toolkit
|
|
mamba create -n whisper-ollama python=3.10 nvidia/label/cuda-12.2.0::cuda-toolkit cudnn -c nvidia -c conda-forge -y
|
|
|
|
# Activate the environment
|
|
mamba activate whisper-ollama
|
|
|
|
# Install Audio and Logic dependencies
|
|
# Note: portaudio is required for sounddevice to work on Linux
|
|
sudo apt-get update && sudo apt-get install libportaudio2 -y
|
|
|
|
pip install faster-whisper sounddevice numpy pyperclip requests
|
|
```
|