Conda setup for Whisper + Torch (recommended)

NOTE: See the project status in REMAINING_FUNCTIONALITY.md for the latest implementation details.

This guide explains how to create a reproducible conda environment that avoids OpenMP runtime conflicts on macOS and provides a stable runtime for faster-whisper / whisper and torch.

Prerequisites - Install Miniforge or Miniconda and ensure conda is on your PATH.

Create environment (CPU example)

conda create -n evospiken-whisper python=3.9 -y
conda activate evospiken-whisper
# Install PyTorch (CPU) from pytorch + conda-forge
conda install -c pytorch -c conda-forge pytorch torchvision torchaudio cpuonly -y
# Install faster-whisper via pip
pip install -r requirements-whisper.txt

# Set whisper model env vars
export VIDEO_ANALYSIS_WHISPER_MODEL=tiny
export VIDEO_ANALYSIS_WHISPER_DEVICE=cpu

# Run smoke
python3 tools/whisper_smoke.py

GPU note: if you have CUDA, follow the PyTorch official instructions at https://pytorch.org to install the correct CUDA-enabled packages, instead of installing cpuonly.

Why this helps - Installing pytorch and numpy from conda-compatible channels reduces the chance of multiple conflicting OpenMP runtimes being pulled in (pip wheels vs system libraries).