John Lightner
f40ca2b3fb
docs(01-01): complete core pipeline plan
...
- Add 01-01-SUMMARY.md with execution results
- Update STATE.md with plan progress and decisions
- Update ROADMAP.md and REQUIREMENTS.md
2026-04-11 02:13:43 -05:00
John Lightner
5a233898c8
feat(01-01): create hum2inst.py CLI pipeline script
...
- Single-file CLI wrapping ACE-Step XL-SFT cover mode
- argparse with --instrument, --output, --strength, --duration flags
- Auto-detect input WAV duration via torchaudio
- Caption templates for piano, guitar, saxophone, violin, flute
- CUDA GPU check with clear error message
- Silence detection on output audio
- User-friendly output naming with instrument + timestamp
2026-04-11 02:11:53 -05:00
John Lightner
262ee6f7d1
chore(01-01): archive experimental scripts
...
- Move midi_to_audio.py to archive/
- Move musicgen_melody.py to archive/
2026-04-11 02:10:59 -05:00
John Lightner
b9cc6121f3
docs(01-core-pipeline): create phase plan
2026-04-11 02:07:27 -05:00
John Lightner
b9932b08b4
docs(core-pipeline): research phase domain
2026-04-11 02:03:30 -05:00
John Lightner
5a04fc3498
docs(01): capture phase context
2026-04-11 01:58:51 -05:00
John Lightner
b7260bbd26
docs: create roadmap (4 phases)
2026-04-11 01:45:42 -05:00
John Lightner
93bd57d386
docs: define v1 requirements
2026-04-11 01:40:49 -05:00
John Lightner
b51cf7cd6b
docs: complete project research for AI Music Pipeline
...
Research covers technology stack (ACE-Step vs MusicGen), feature
landscape, MusicGen melody architecture analysis, and domain pitfalls.
Key finding: ACE-Step 1.5 cover mode is the proven primary engine;
MusicGen via HF transformers has fundamental conditioning flaws.
2026-04-11 01:31:32 -05:00
John Lightner
9d613bdcad
chore: add project config
2026-04-11 01:15:32 -05:00
John Lightner
6fb0181b08
docs: initialize project
2026-04-11 01:14:30 -05:00
