4 Commits

Author	SHA1	Message	Date
Your Name	d1e1fedcae	fix: Resolve issues #7, #8, #9 - moviepy, transformers, Whisper OOM ... Issue #7: Handle moviepy 2.x removing verbose param from write_audiofile Issue #8: Pin transformers<5.0.0 to fix summarization pipeline task registry Issue #9: Add Whisper model memory warnings and OOM error handling	2026-03-03 02:10:52 -05:00
Your Name	70c5d32413	feat: Add streaming Ollama support, model caching, and UI improvements ... - Add streaming summarization via Ollama API (stream_summarize_with_ollama) - Cache ML models with @st.cache_resource (diarization, NER, translation, Whisper) - Add temp file cleanup for extracted audio - Add system capabilities detection (FFmpeg, GPU info) - Add get_video_duration utility - Improve validation with FFmpeg check - Rewrite app.py with streaming support and UI enhancements - Clean up redundant comments and unused imports across all utils	2026-02-18 10:26:09 -05:00
Your Name	ce398ae1d4	fix: Update moviepy import for v2.x compatibility (closes #6) ... moviepy 2.x removed the moviepy.editor submodule. Import AudioFileClip directly from moviepy with a fallback for moviepy 1.x users. Also close the audio clip after writing to prevent resource leaks. Co-authored-by: Cursor <cursoragent@cursor.com>	2026-02-13 00:15:07 -05:00
DataAnts-AI	3c44257d8a	Updated with code	2025-01-28 17:00:03 -05:00