34 lines
511 B
Plaintext
34 lines
511 B
Plaintext
|
# FastAPI backend
|
||
|
|
fastapi>=0.115.0
|
||
|
|
uvicorn[standard]>=0.32.0
|
||
|
|
websockets>=14.0
|
||
|
|
python-multipart>=0.0.12
|
||
|
|
|
||
|
|
# Transcription (WhisperX for word-level alignment)
|
||
|
|
whisperx>=3.1.0
|
||
|
|
faster-whisper>=1.0.0
|
||
|
|
|
||
|
|
# Audio / Video processing
|
||
|
|
moviepy>=1.0.3
|
||
|
|
ffmpeg-python>=0.2.0
|
||
|
|
soundfile>=0.10.3
|
||
|
|
|
||
|
|
# ML / GPU
|
||
|
|
torch>=2.0.0
|
||
|
|
torchaudio>=2.0.0
|
||
|
|
numpy>=1.24.0
|
||
|
|
|
||
|
|
# Speaker diarization
|
||
|
|
pyannote.audio>=3.1.1
|
||
|
|
|
||
|
|
# AI providers
|
||
|
|
openai>=1.50.0
|
||
|
|
anthropic>=0.39.0
|
||
|
|
requests>=2.28.0
|
||
|
|
|
||
|
|
# Audio cleanup
|
||
|
|
deepfilternet>=0.5.0
|
||
|
|
|
||
|
|
# Utilities
|
||
|
|
pydantic>=2.0.0
|