dschlueter/Musiksammlung
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
Musiksammlung/tests
History
dschlueter 1753ab204f Add Vision-LLM mode for direct image-to-JSON extraction 
Tesseract OCR fails on rotated/low-contrast CD back covers.
New vision_llm module sends images directly to qwen3-vl via
Ollama chat API, bypassing OCR entirely. Robust JSON extraction
handles thinking tags, markdown blocks, and empty responses.
CLI scan/process commands gain --vision flag.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-15 01:35:05 +01:00
..
__init__.py Add project skeleton: CLI pipeline for CD digitization 2026-02-15 01:00:12 +01:00
test_models.py Add project skeleton: CLI pipeline for CD digitization 2026-02-15 01:00:12 +01:00
test_organizer.py Add project skeleton: CLI pipeline for CD digitization 2026-02-15 01:00:12 +01:00
test_playlist.py Add project skeleton: CLI pipeline for CD digitization 2026-02-15 01:00:12 +01:00
test_vision_llm.py Add Vision-LLM mode for direct image-to-JSON extraction 2026-02-15 01:35:05 +01:00