Instructions to use sammoran-phd/cara-native-musicgen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Audiocraft
How to use sammoran-phd/cara-native-musicgen with Audiocraft:
from audiocraft.models import MusicGen model = MusicGen.get_pretrained("sammoran-phd/cara-native-musicgen") descriptions = ['happy rock', 'energetic EDM', 'sad jazz'] wav = model.generate(descriptions) # generates 3 samples. - Notebooks
- Google Colab
- Kaggle
| { | |
| "format": "cara_source_snapshot_v1", | |
| "git_remote": "https://github.com/sammoran78/cara-native-musicgen.git", | |
| "git_head": "896ec7c47f5e5d1e5aa1e4b260c4405328bf009d", | |
| "worktree_clean": false, | |
| "worktree_status": [ | |
| "M audiocraft/data/audio_dataset.py", | |
| " M audiocraft/data/music_dataset.py", | |
| " M audiocraft/models/builders.py", | |
| " M audiocraft/models/lm.py", | |
| " M audiocraft/models/musicgen.py", | |
| " M audiocraft/solvers/musicgen.py", | |
| " M config/model/lm/default.yaml", | |
| "?? .amlignore", | |
| "?? audiocraft/modules/cara_vocab.py", | |
| "?? docs/CARA_NATIVE_MUSICGEN_INTEGRATION_LOG.md", | |
| "?? huggingface/", | |
| "?? manifests/", | |
| "?? outputs/", | |
| "?? scripts/benchmark_cara_fixed_audio.py", | |
| "?? scripts/benchmark_cara_native_musicgen.py", | |
| "?? scripts/cara_native_toy_overfit.py", | |
| "?? scripts/expand_cara_vocab.py", | |
| "?? scripts/export_cara_native_musicgen_manifest.py", | |
| "?? scripts/extract_cara_probe_features.py", | |
| "?? scripts/prompt_semantic_ablation.py", | |
| "?? scripts/score_cara_attribution_predictions.py", | |
| "?? scripts/score_cara_native_suffix_structure.py", | |
| "?? scripts/train_cara_native_musicgen.py", | |
| "?? scripts/verify_cara_checkpoint_expansion.py", | |
| "?? scripts/verify_cara_delay_masks.py", | |
| "?? scripts/verify_cara_native_suffix_generation.py", | |
| "?? scripts/verify_cara_native_training_preflight.py", | |
| "?? tests/data/test_music_dataset.py", | |
| "?? tests/modules/test_cara_vocab.py", | |
| "?? tests/scripts/", | |
| "?? tests/solvers/", | |
| "?? tests/test_prompt_semantic_ablation.py" | |
| ], | |
| "source_archive": "cara-native-musicgen-source.tar.gz", | |
| "source_archive_sha256": "a6f9f6bc94266edccbafe8e608c9f3fa9b9205078f49c56c40e39e3b03a533c3", | |
| "note": "The archive is authoritative when worktree_clean is false." | |
| } | |