Instructions to use sammoran-phd/cara-native-acestep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sammoran-phd/cara-native-acestep with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="sammoran-phd/cara-native-acestep")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("sammoran-phd/cara-native-acestep", device_map="auto") - PEFT
How to use sammoran-phd/cara-native-acestep with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
| license: mit | |
| library_name: transformers | |
| pipeline_tag: text-to-audio | |
| base_model: | |
| - ACE-Step/acestep-5Hz-lm-0.6B | |
| - ACE-Step/Ace-Step1.5 | |
| tags: | |
| - ace-step | |
| - music | |
| - cara | |
| - attribution | |
| - peft | |
| - research | |
| # CARA-native ACE-Step | |
| This peer-review release contains the two checkpoint-owned ACE-Step interfaces | |
| used after Phase 1: | |
| - Phase 2: a CARA-expanded and fine-tuned 0.6B 5 Hz planner LM. | |
| - Exploratory Phase 3: the joint turbo-DiT LoRA adapter plus hierarchical | |
| 98-pool/9-family CARA attribution head. | |
| The Phase 3 adapter does not duplicate the multi-gigabyte base DiT. It reloads | |
| against the named public ACE-Step base model, keeping the derivative release | |
| small and making the base/adapter boundary explicit. | |
| ## Contents | |
| - `phase2/lm/`: `save_pretrained` LM and tokenizer files plus the SFT report. | |
| - `phase3/adapter/`: PEFT LoRA adapter for the turbo-DiT. | |
| - `phase3/cara_attribution_head.pt`: checkpoint-owned pool/family head. | |
| - `phase3/phase3_checkpoint_manifest.json`: base/adapter/head contract. | |
| - `registry/`: the exact CARA registry required by both interfaces. | |
| - `evidence/`: authoritative Phase 2 and exploratory Phase 3 reports. | |
| - `source/`: an exact source snapshot used to load and evaluate the checkpoints. | |
| - `cara_model_manifest.json`: byte sizes and SHA-256 values for release files. | |
| Use the immutable `phase2-v1` tag, or its resolved Hub commit hash. | |
| ## Reload Phase 2 | |
| ```bash | |
| hf download sammoran-phd/cara-native-acestep \ | |
| --revision phase2-v1 \ | |
| --local-dir cara-native-acestep-release | |
| mkdir cara-native-acestep-source | |
| tar -xzf cara-native-acestep-release/source/cara-native-acestep-source.tar.gz \ | |
| -C cara-native-acestep-source | |
| cd cara-native-acestep-source | |
| python - <<'PY' | |
| from pathlib import Path | |
| from scripts.benchmark_cara_native_acestep import initialize_lm | |
| handler = initialize_lm( | |
| Path("../cara-native-acestep-release/phase2/lm").resolve() | |
| ) | |
| print(type(handler).__name__) | |
| PY | |
| ``` | |
| For Phase 3, load the public ACE-Step turbo-DiT through the included fork, then | |
| pass `phase3/` as `--phase3_checkpoint_dir`; the evaluator loads the PEFT adapter | |
| and `cara_attribution_head.pt` together. The complete locked commands are in | |
| the `cara-native-musicmodels` Phase 2/3 job specifications. | |
| ## Evaluation boundary | |
| The Phase 2 0.6B planner interface remained below its predeclared | |
| representation/discriminability ceiling. On the 780-waveform balanced | |
| fixed-audio core it scored 1.92% exact top-1, 3.46% top-3, 13.46% family | |
| accuracy, and 100% registry-valid output. Those are real results, but they are | |
| below-ceiling ablation evidence rather than a passed scientific gate. | |
| On the matched exploratory Phase 3 436-waveform comparison, the joint | |
| DiT-LoRA-plus-head checkpoint scored 4.13% exact top-1, 10.78% top-3, 30.50% | |
| pool-derived family accuracy, and 32.11% direct family accuracy. The broad-family | |
| gain is intervention-specific; exact pool attribution did not improve. | |
| ## Intended use and limitations | |
| This release is intended for research reproduction and controlled interface | |
| auditing. It is not a provenance, source-identification, royalty allocation, or | |
| safety system. Results come from one source corpus and one training run per | |
| checkpoint. Phase 3 is explicitly exploratory. | |
| ## License | |
| The ACE-Step code and named public base checkpoints are MIT licensed. Retain the | |
| included license and upstream attribution when redistributing this release. | |