Commit History

  1. chore: remove sensitive thesis docs and notebooks from public repository

    541b62c
  2. docs: add cloud multimodala fusion notebook for GPU inference

    7b718a5
  3. docs: finalize deployment troubleshooting guide and mark tasks 100% complete

    f019efa

  1. fix: revert to native python:3.10-slim with CMAKE_BUILD_PARALLEL_LEVEL=1 to fix dlib numpy pybind ABI conflict

    2f53b35
  2. fix: enforce contiguous uint8 arrays for dlib and remove redundant rgb-bgr conversions

    3cac69c
  3. fix: correct GenConViT weight download directory path to be inside GenConViT package

    d95c9f9
  4. fix: add missing albumentations dependency for GenConViT inference

    0be26ec
  5. fix: replace obsolete libgl1-mesa-glx with libgl1 for debian trixie

    c2c2e92
  6. fix: replace python base image with miniconda to install precompiled dlib via conda and avoid OOM

    2715a69
  7. fix: set MAX_JOBS=1 to prevent dlib C++ compilation OOM on HF Spaces

    e4bfe11
  8. fix: quote dlib package string in Dockerfile to prevent shell redirection

    f5d6707
  9. fix: resolve OOM crash (CPU torch, isolated dlib) and Pillow 11 compatibility

    23d2658
  10. fix: add all missing GenConViT deps (opencv-headless, dlib, face-recognition, decord, timm, torchvision)

    1e9de5e
  11. fix: video import collision via importlib + auto-download GenConViT weights at startup

    892041c
  12. fix: pin gradio and starlette versions to bypass Starlette TemplateResponse breaking change

    5a57f8e
  13. fix: monkey-patch gradio_client bool-schema crash at runtime before import

    45dd989
  14. fix: replace gr.Code with gr.Textbox + show_api=False to fix bool-schema crash

    3be6b3a
  15. fix: remove button_primary_shadow from theme (unsupported in Gradio 4.44+)

    e551dd8
  16. fix: pin huggingface_hub<0.26 to fix HfFolder crash, add .hfignore

    bb780a3
  17. Fix Hugging Face configuration and update docs

    b4b50cc
  18. Merge branch 'main' of https://huggingface.co/spaces/Aryanaideveloper/Multimodal_Deepfake_Detection

    9f2e3de
  19. Finalizing Thesis Multimodal Architecture for Hugging Face

    089c099
  20. initial commit

    Unverified signature
    3ed683d

  1. feat: implement fairseq compatibility shim and working audio inference pipeline⁠

    Aryanaideveloper +1: Claude Opus 4.6
    0f96bb5

  1. feat: initial project setup with audio/video detection modules and fusion⁠

    Aryanaideveloper +1: Claude Opus 4.6
    5cc48fc