Go to file
Krzysztof kuhy Rudnicki 740726a3ae music_gen: add segmented generation, Bark vocals, and song mixing
- Add segmented generation with crossfading for long audio (>30s)
- Add Bark integration for speech/vocal generation (--speech flag)
- Add full song generation with vocals over instrumental (--song flag)
- Auto-select MusicGen model size based on available VRAM
- Enforce CUDA for NVIDIA GPUs (no CPU fallback)
- Update README with new features and examples
2025-12-04 21:26:52 +01:00
.github Expand copilot-instructions with C engine and python_pkg details 2025-12-02 22:18:40 +01:00
.vscode fix: correct shebang and executable permissions 2025-11-30 13:42:16 +01:00
articles fix(lint): convert os.path to pathlib - remove PTH per-file ignores 2025-11-30 23:03:03 +01:00
C fix: resolve shellcheck warnings 2025-11-30 13:48:17 +01:00
CPP fix: correct shebang and executable permissions 2025-11-30 13:42:16 +01:00
LaTeX fix: correct shebang and executable permissions 2025-11-30 13:42:16 +01:00
poker_modifier_app fix(lint): LOG015 - replace root logger with module loggers 2025-11-30 21:59:24 +01:00
python_pkg music_gen: add segmented generation, Bark vocals, and song mixing 2025-12-04 21:26:52 +01:00
sonic_pi feat: accept first argument as audio by defauilt sonic pi 2025-10-26 16:33:37 +01:00
TS fix: correct shebang and executable permissions 2025-11-30 13:42:16 +01:00
.gitignore gitignore: add music_gen output folder 2025-12-04 20:59:13 +01:00
.pre-commit-config.yaml Add local AI music generator using Meta's MusicGen 2025-12-04 20:43:44 +01:00
LICENSE chore: updated Licenses 2024-09-11 15:02:50 +02:00
lint_python.sh fix: resolve shellcheck warnings 2025-11-30 13:48:17 +01:00
pyproject.toml Add local AI music generator using Meta's MusicGen 2025-12-04 20:43:44 +01:00
pytest.ini feat: C engine 2025-09-06 18:26:31 +02:00
requirements-dev.txt fix: correct shebang and executable permissions 2025-11-30 13:42:16 +01:00
requirements.txt refactor: clean up pyproject.toml - remove defaults and redundant configs 2025-12-01 16:33:42 +01:00
test_input_clean.wav fix: getting rnnoise model 2025-10-12 18:57:55 +02:00
test_input.wav fix: getting rnnoise model 2025-10-12 18:57:55 +02:00