Spaces:
Runtime error
Runtime error
Commit History
-
Group words into proper subtitle segments
Whisper Transcriber Bot- Add group_words_into_segments() to combine word-level timestamps - Group by: sentence punctuation, max 12 words, max 7 seconds - Update SRT and VTT formatters to use grouped segments - Much easier to edit subtitles nowd33fc74 -
Fix Gradio version in README and default to tiny model
Whisper Transcriber Bot- Update sdk_version in README.md from 4.16.0 to 4.44.0 - Default model size to 'tiny' for better compatibility with free Spaces72f1983 -
Update README.md
Verified signature64273cc -
Fix torchaudio compatibility and update Gradio version
Whisper Transcriber Bot- Add torchaudio with version bounds to fix AudioMetaData error - Update Gradio from 4.16.0 to >=4.44.0 (security fix) - Add version bounds to prevent future compatibility issues3638da8 -
Use Gradio 4.16.0 - stable version without API schema bugs
Whisper Transcriber Bote8ece31 -
Simplify to minimal clean interface - default HF style
Whisper Transcriber Bot7f464b5 -
Use stable Gradio 4.44.1 (latest 4.x, secure and compatible)
Whisper Transcriber Bot14efc79 -
Fix: Redesign UI for Gradio 5.x compatibility with cleaner tab-based layout
Whisper Transcriber Boteff77b5 -
Fix: Remove gr.Examples to prevent YouTube URL resolution error at startup
Whisper Transcriber Bot3fc26fb -
Update Gradio to v5.0.0 to fix security vulnerabilities
Whisper Transcriber Bot22b7c5d -
Initial commit: Complete Whisper Transcriber implementation
Whisper Transcriber BotFeatures: - Audio/video file upload support - YouTube & direct URL download - 3 Whisper models (tiny/small/medium) - Auto language detection (99+ languages) - Multiple output formats (SRT, VTT, TXT, JSON) - Optional speaker diarization - Large file chunking (30-min segments) - Real-time progress tracking - Public API endpoint - Comprehensive documentation Built with OpenAI Whisper, Gradio, and PyTorch4051511 -
initial commit
Verified signaturefa2fbf6