Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Spaces:

Duplicated fromΒ  vidhi0405/VideoToText

LogicGoInfotechSpaces
/
VideoToText
Sleeping

App Files Files Community
Fetching metadata from the HF Docker repository...
VideoToText
157 kB
  • 4 contributors
History: 49 commits
HariLogicgo's picture
HariLogicgo
Prioritize explicit incident facts in reporter-style descriptions
89c6921 about 14 hours ago
  • src
    commit 3 about 16 hours ago
  • .DS_Store
    6.15 kB
    Comprehensive fix for HuggingFace cache directory permissions 5 months ago
  • .gitattributes
    1.52 kB
    initial commit 5 months ago
  • .gitignore
    108 Bytes
    πŸ”§ Update .gitignore to exclude video files and cache 5 months ago
  • DEPLOYMENT_UPDATE.md
    3.67 kB
    πŸš€ Deploy optimized SmolVLM2 video highlights with 80% success rate 5 months ago
  • Dockerfile
    825 Bytes
    πŸš€ Deploy optimized SmolVLM2 video highlights with 80% success rate 5 months ago
  • README.md
    2.64 kB
    commit 3 about 16 hours ago
  • app.py
    9.8 kB
    Improve reporter-style output accuracy and fix description pipeline about 15 hours ago
  • audio_enhanced_highlights_final.py
    26 kB
    Improve reporter-style output accuracy and fix description pipeline about 15 hours ago
  • fastapi_requirements.txt
    301 Bytes
    Fix PyAV dependency for video processing 5 months ago
  • highlights_api.py
    14.8 kB
    Improve reporter-style output accuracy and fix description pipeline about 15 hours ago
  • huggingface_exact_approach.py
    39 kB
    Prioritize explicit incident facts in reporter-style descriptions about 14 hours ago
  • huggingface_segment_highlights.py
    26.2 kB
    commit 3 about 16 hours ago
  • requirements.txt
    727 Bytes
    Fix PyAV dependency for video processing 5 months ago
  • test_api.py
    2.05 kB
    commit 3 about 16 hours ago