ACappellaSet models
License scope
| Material | License / Terms |
|---|---|
| ACappellaSet contributions to the 29 released model checkpoints | CC BY-NC 4.0, to the extent of rights held by the ACappellaSet contributors. See license text. |
| Embedded third-party pretrained weights and encoders | Subject to applicable upstream terms and permissions. See WEIGHTS_NOTICE.md. |
| Original documentation and metadata | MIT (LICENSE) |
| Original source code | MIT (GitHub LICENSE), subject to third-party notices. |
The MIT license does not apply to model weights.
The CC BY-NC 4.0 designation does not relicense third-party pretrained parameters. Redistribution permissions for upstream-derived weights remain subject to verification.
Dataset audio is governed by its separate Dataset Terms.
Model weights and release metadata for a cappella source separation.
The public release contains 29 checkpoints: three fixed-output models, twelve original part-specific specialists, and fourteen conditioned selections, including two trained with AI-generated singer augmentation. Downloads do not require login or an access request.
- Checkpoint paths, hashes, configurations, and validation selections: manifest.json
- Code and installation: ACappellaSet on GitHub
- Inference: fixed-output and part-specific models, shared query-conditioned models.
- Training and configurations: published code and recipes.
- Dataset: ACappellaSet is released with Manual Approval for Non-commercial Research Use. Model downloads do not require dataset access approval, and Dataset Terms do not relicense these model weights.
Fixed-output and part-specific models
These models use the HTDemucs-MSS architecture, with parallel waveform and spectrogram branches coupled by a cross-domain Transformer. Fixed-output models predict six vocal parts simultaneously. Each part-specific model has a two-output head for its designated target and residual, with a separate checkpoint per vocal part; no query input is required.
JC denotes JaCappella; SK denotes natural Seagull-K recordings; JC + SK denotes joint training. Each checkpoint below links to its file.
| Model | Training corpus | Checkpoints |
|---|---|---|
| Fixed-output HTDemucs (6 outputs) | JC | Fixed_6stem_htdemucs_JC |
| Fixed-output HTDemucs (6 outputs) | SK | Fixed_6stem_htdemucs_SK |
| Fixed-output HTDemucs (6 outputs) | JC + SK | Fixed_6stem_htdemucs_SKnJC |
| Part-specific HTDemucs (mixture input) | JC | Soprano, Alto, Tenor, Bass, VP, Lead |
| Part-specific HTDemucs (mixture input) | SK | Soprano, Alto, Tenor, Bass, VP, Baritone |
Shared query-conditioned
These models extend HTDemucs with query-conditioned FiLM layers in the waveform and spectrogram branches before the cross-domain Transformer. Queries use a learned vocal-part embedding, a matching fine-tuned ReDimNet2 singer-enrollment encoder, or both. A shared model extracts the requested target and its residual; the full-remix and single-clone models use the singer-conditioned architecture with different training data.
Checkpoint labels show the selected training step and validation criterion. “Pooled” means JC + SK validation.
| Model | Training data | Checkpoint (validation criterion) |
|---|---|---|
| Vocal-part-conditioned HTDemucs | SK | 4k (JC inclusive); 198k (SK shared) |
| Vocal-part-conditioned HTDemucs | JC | 119k (SK inclusive); 141k (JC shared) |
| Singer-conditioned HTDemucs | SK | 12k (JC shared, JC inclusive); 106k (pooled shared, pooled inclusive); 179k (SK shared) |
| Vocal-part + singer-conditioned HTDemucs | SK | 7k (JC inclusive) |
| Singer-conditioned HTDemucs | JC | 184k (SK inclusive) |
| Vocal-part + singer-conditioned HTDemucs | JC | 188k (SK inclusive) |
| Singer-conditioned HTDemucs | JC + SK | 195k (JC shared, pooled shared); 198k (SK shared) |
| Singer-conditioned HTDemucs | SK + full-remix singer augmentation | 131k (pooled inclusive) |
| Singer-conditioned HTDemucs | SK + single-clone singer augmentation | 48k (pooled inclusive) |
Conditioned runs were trained through 200k updates; the released files were selected using validation scores. Training data and validation corpus are separate attributes.
Shared aggregates retained S/A/T/B/VP pairs rather than averaging five part means. Inclusive additionally includes JC Lead or SK Bar. In the machine-readable registry, combined_* selection labels mean pooled JC + SK validation.
Download and inference
hf download AcappellaSet/ACappellaSet-Models --local-dir ./ACappellaSet-Models
To download one checkpoint, add its file path from the tables above after the repository name. Follow the linked GitHub installation and inference guides and pass the downloaded file with --checkpoint. The registry records inference_model_id and, for shared query-conditioned models, the available selection_labels. Released files contain inference tensors only (plus the selected step for query-conditioned models) and load with weights_only=True. Checkpoint and configuration hashes are verified before strict loading.
Fixed-output and part-specific models take mixture audio. Shared query-conditioned models additionally use a vocal-part query, singer-enrollment audio, or both, according to their conditioning type. All 29 checkpoints have registered inference adapters. Singer- and dual-conditioned exports include their matching fine-tuned encoder tensors.
Output conventions
The fixed-output JC + SK model returns vp, bass, soprano, alto, tenor, and other.
Its other output has JC Lead / SK Baritone training semantics; these are not
independent outputs. Part-specific specialists use residual index 0 and target
index 1. Shared query-conditioned models use target index 0 and residual index 1. Preserve each checkpoint's native source order and inference settings.
Layout
manifest.json
fixed/{JC,SK,SKnJC}/legacy/
specialists/{JC,SK}/legacy/{part}/
conditioned/
configs/
model.json and conditioned step JSON files record checkpoint identity, configuration, and license. bank.json maps specialist roles to model IDs. The registry provides released-file SHA-256 hashes. Configurations are included under configs/; maintained executable code is on GitHub.
Validation-selected models record the validation corpus, shared/inclusive scope, training cutoff, and selected step. Multiple selectors may refer to the same file. The two AI-augmented entries identify their augmentation datasets explicitly.
Licenses and citation
Original repository documentation and metadata use the MIT license, which does not apply to model weights. ACappellaSet contributions to the released checkpoints use CC BY-NC 4.0, to the extent of rights held by the contributors. This designation does not relicense embedded third-party pretrained parameters; upstream redistribution permissions remain subject to verification. Preserve attribution and indicate changes when sharing. See License scope and weight notices. Dataset audio is separate. Upstream architecture attribution is maintained in the GitHub repository's third-party notices.
Cite the accompanying paper when a verified citation becomes available; do not infer publication status from this repository.