Downloads · 30 days
0
jeanaewaxy/sveet
sveet is a machine learning model from jeanaewaxy. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Anonymous release accompanying a submission under double-blind review. The code that loads the checkpoint and renders the data is in the anonymous code repository linked from the paper.
Downloads · 30 days
0
Access
Public
Updated Sep 16, 2026
Repo size
418 MB
Likes
0
Public
Click a slice to open those files.
.ckpt263 MB · 63%
From the Hugging Face model README
Anonymous release accompanying a submission under double-blind review. The code that loads the checkpoint and renders the data is in the anonymous code repository linked from the paper.
| File | Content |
|---|---|
sveet_ms_ep46.ckpt | SVEET-MS, final checkpoint (epoch 46, 528,750 updates), EMA weights, 65.7M parameters, PyTorch Lightning format reduced to weights and hyperparameters |
data/aug_train_manifest.csv.gz | 720,000-pair training recipe (1:1 speech:singing, 1000 h) with every degradation parameter |
data/aug_valid_manifest.csv.gz | 66,876-pair singing validation recipe |
benchmark/benchmark_public.tgz | the two Acapella conditions of the singing benchmark (MIR-1K and OpenSinger sources): degraded inputs, clean references and the outputs of every evaluated system, FLAC 44.1 kHz stereo |
Source paths inside the manifests are relative to the corpus roots (GTSinger/...,
Singing/<corpus>/..., Speech/<corpus>/..., interference_pool/...); see data/README.md
in the code repository for the rendering procedure. No corpus audio is redistributed;
the manifests are released under CC BY 4.0 and the checkpoint under MIT; the benchmark excerpts are derived from MIR-1K and OpenSinger and are distributed for research use under the terms of those corpora (OpenSinger: CC BY-NC-SA 4.0).