requirements.txt

# ShortSmith v2 - Requirements
# For Hugging Face Spaces deployment

# ============================================
# Core Dependencies
# ============================================

# Gradio UI framework
gradio==4.44.1

# Pin pydantic to fix "argument of type 'bool' is not iterable" error
pydantic==2.10.6

# Deep learning frameworks
torch>=2.0.0
torchvision>=0.15.0
torchaudio>=2.0.0

# Transformers and model loading
transformers>=4.35.0
accelerate>=0.24.0
bitsandbytes>=0.41.0  # For INT4/INT8 quantization

# ============================================
# Video Processing
# ============================================

# Video I/O
ffmpeg-python>=0.2.0
opencv-python-headless>=4.8.0

# Scene detection
scenedetect[opencv]>=0.6.0

# ============================================
# Audio Processing
# ============================================

# Audio analysis
librosa>=0.10.0
soundfile>=0.12.0

# Optional: Advanced audio understanding
# wav2vec2 is loaded via transformers

# ============================================
# Computer Vision Models
# ============================================

# Face recognition
insightface>=0.7.0
onnxruntime-gpu>=1.16.0  # Use onnxruntime for CPU-only

# Person detection (YOLO)
ultralytics>=8.0.0

# Image processing
Pillow>=10.0.0

# ============================================
# Utilities
# ============================================

# Numerical computing
numpy>=1.24.0

# Progress bars
tqdm>=4.65.0

# ============================================
# Hugging Face Specific
# ============================================

# For model downloading
huggingface_hub>=0.17.0

# Qwen2-VL specific utilities
qwen-vl-utils>=0.0.2

# ============================================
# Optional: GPU Acceleration
# ============================================

# Uncomment for specific CUDA versions if needed
# --extra-index-url https://download.pytorch.org/whl/cu118
# torch==2.1.0+cu118
# torchvision==0.16.0+cu118

# ============================================
# Training Dependencies (optional)
# ============================================

# For loading Mr. HiSum dataset
h5py>=3.9.0

# ============================================
# Development Dependencies (optional)
# ============================================

# pytest>=7.0.0
# black>=23.0.0
# isort>=5.0.0
# mypy>=1.0.0