requirements.txt

# Core Dependencies
torch>=2.0.0
torchaudio>=2.0.1
transformers>=4.30.0
openai-whisper>=20230314
faster-whisper>=1.0.3
ctranslate2>=4.0.0
Pillow>=9.5.0
numpy>=1.24.0
soundfile>=0.12.1
scipy>=1.10.0
onnx>=1.14.0
onnxscript>=0.5.0
PyNaCl>=1.5.0

# Audio Processing & Streaming
pydub>=0.25.1
librosa>=0.10.0
sounddevice>=0.4.6      # Primary microphone capture (PortAudio-backed)
pyaudio>=0.2.14         # Alternate microphone capture (PortAudio-backed)
pyttsx3>=2.90           # Offline TTS engine for Meta provider

# Vision & Image Processing
opencv-python>=4.8.0
matplotlib>=3.7.0

# Optional (for later sessions)
tesseract                 # For OCR in Week 7 (note: installed via system package in Colab)
gTTS                     # Text-to-speech (for audio reply, Week 11+)
gradio                   # Web app prototype (Week 18 optional)
fastapi                  # API serving (Week 18 optional)
uvicorn[standard]        # ASGI server for FastAPI-based endpoints

# Validation & schema tooling
jsonschema>=4.21.1
pydantic>=2.0.0           # Wire protocol models and FastAPI integration

# Colab-specific (auto-installed in Colab but listed for local testing)
ipython
notebook