51 lines
1.3 KiB
Plaintext
51 lines
1.3 KiB
Plaintext
# OBS Recording Transcriber Dependencies
|
|
# Core dependencies with pinned compatible versions
|
|
streamlit==1.26.0
|
|
moviepy==1.0.3
|
|
openai-whisper==20231117
|
|
requests>=2.28.0
|
|
humanize>=4.6.0
|
|
|
|
# PyTorch ecosystem - pinned for compatibility
|
|
torch==2.0.1
|
|
torchaudio==2.0.2
|
|
torchvision==0.15.2
|
|
|
|
# Transformers ecosystem - compatible versions
|
|
transformers==4.30.2
|
|
tokenizers==0.13.3
|
|
|
|
# ML dependencies with compatible versions
|
|
numpy==1.24.3
|
|
scipy==1.10.1
|
|
scikit-learn==1.3.0
|
|
|
|
# Audio processing and ML models
|
|
pyannote.audio==3.1.1
|
|
pytorch-lightning==2.0.6
|
|
|
|
# Other dependencies
|
|
iso639>=0.1.4
|
|
protobuf>=3.20.0,<4.0.0
|
|
matplotlib>=3.5.0
|
|
soundfile>=0.10.3
|
|
ffmpeg-python>=0.2.0
|
|
|
|
# Optional: Ollama Python client (uncomment to install)
|
|
# ollama
|
|
|
|
# Installation notes:
|
|
# 1. For Windows users, you may need to install PyTorch separately:
|
|
# pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
|
|
#
|
|
# 2. For tokenizers issues, try installing Visual C++ Build Tools:
|
|
# https://visualstudio.microsoft.com/visual-cpp-build-tools/
|
|
#
|
|
# 3. For pyannote.audio, you'll need a HuggingFace token with access to:
|
|
# https://huggingface.co/pyannote/speaker-diarization-3.0
|
|
#
|
|
# 4. FFmpeg is required for audio processing:
|
|
# Windows: https://www.gyan.dev/ffmpeg/builds/
|
|
# Mac: brew install ffmpeg
|
|
# Linux: apt-get install ffmpeg
|