Add installation scripts and update documentation for Phase 3 features
This commit is contained in:
@ -1,5 +1,42 @@
|
||||
# OBS Recording Transcriber Dependencies
|
||||
# Core dependencies
|
||||
streamlit==1.26.0
|
||||
moviepy==1.0.3
|
||||
whisper
|
||||
transformers==4.21.1
|
||||
openai-whisper>=20230314
|
||||
transformers>=4.21.1
|
||||
torch>=1.7.0
|
||||
torchaudio>=0.7.0
|
||||
requests>=2.28.0
|
||||
humanize>=4.6.0
|
||||
|
||||
# Phase 2 dependencies
|
||||
scikit-learn>=1.0.0
|
||||
numpy>=1.20.0
|
||||
|
||||
# Phase 3 dependencies
|
||||
pyannote.audio>=2.1.1
|
||||
iso639>=0.1.4
|
||||
protobuf>=3.20.0,<4.0.0
|
||||
tokenizers>=0.13.2
|
||||
scipy>=1.7.0
|
||||
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
|
||||
|
||||
Reference in New Issue
Block a user