requirements.txt

# Core framework
fastapi>=0.109.0
uvicorn[standard]>=0.27.0
python-multipart>=0.0.6
jinja2>=3.1.2
aiofiles>=23.2.1

# AI/ML - Speech-to-Text
faster-whisper>=1.0.0
ctranslate2>=4.0.0

# AI/ML - Speaker Diarization (from notebook cell #2)
pyannote.audio>=3.3.1
torch>=2.1.0
torchaudio>=2.1.0
torchvision
lightning
torchmetrics


# Transformers Whisper + LoRA
transformers>=4.39.0,<5
accelerate>=0.26.0
peft>=0.8.0
huggingface-hub>=0.20.0
safetensors>=0.4.0


# AI/ML - Vocal Separation
audio-separator[cpu]>=0.17.0
denoiser>=0.1.4

# Audio processing
librosa>=0.10.0
ffmpeg-python>=0.2.0
pydub>=0.25.1

# Configuration
pydantic-settings>=2.1.0
python-dotenv>=1.0.0

# Utilities
numpy>=1.24.0