17 lines
333 B
Plaintext
17 lines
333 B
Plaintext
# Whisper Diarization Enhancement Server
|
|
|
|
fastapi==0.104.1
|
|
uvicorn[standard]==0.24.0
|
|
httpx==0.25.2
|
|
python-multipart==0.0.6
|
|
aiofiles==23.2.1
|
|
scipy>=1.10.0
|
|
numpy>=1.24.0
|
|
librosa>=0.10.0
|
|
soundfile>=0.12.1
|
|
|
|
# Optional — heavier ML models (installed separately if available)
|
|
# pyannote.audio>=3.1.0
|
|
# speechbrain>=0.5.16
|
|
# torch>=2.0.0
|