Skip to content
ModelListedExternal
Download

Free Svc

FreeSVC is a promising multilingual zero-shot singing voice conversion model. It enables the conversion of singing voices across languages without the need for extensive language-specific training. GitHub repository....

Sourcehuggingface.co/alefiury/free-svc/tree/ab1387ccbe1ed5e44187fd0f06ea52a882917ebd
KindOtherVersionRevision ab1387cBgrade

Model source

Kind
Other
File size
351–822 MB
Version
vRevision ab1387c
Updated
Sep 22, 2026
Downloads
95
Source
Hugging Face

Source description

FreeSVC: Zero-shot Multilingual Singing Voice Conversion

FreeSVC is a promising multilingual zero-shot singing voice conversion model. It enables the conversion of singing voices across languages without the need for extensive language-specific training. GitHub repository. Paper arXiv pre-print.

Supported Languages

LanguageIDStatusSpeech DataSinging Data
Chinese0✅ Full255h70h
Dutch1✅ FullPart of CML-
English2✅ Full921h47h
French3✅ FullPart of CML-
German4✅ FullPart of CML-
Italian5✅ FullPart of CML-
Japanese6✅ Full30h-
Other*7⚠️ Partial-10h
Polish8✅ FullPart of CML-
Portuguese9✅ FullPart of CML-
Spanish10✅ FullPart of CML-

*Note: The "Other" category is used for vocal techniques without content.

Model Overview

FreeSVC leverages an enhanced VITS architecture integrated with Speaker-invariant Clustering (SPIN) and the ECAPA2 speaker encoder. This combination effectively separates speaker characteristics from linguistic content, ensuring high-quality and natural-sounding voice conversions across multiple languages.

Training Datasets

FreeSVC was trained on a diverse set of speech and singing datasets covering multiple languages:

DatasetHoursLanguageType
AISHELL-1170hChineseSpeech
AISHELL-385hChineseSpeech
CML-TTS3.1k7 LanguagesSpeech
HiFiTTS292hEnglishSpeech
JVS30hJapaneseSpeech
LibriTTS-R585hEnglishSpeech
NUS (NHSS)7hEnglishSpeech, Singing
OpenSinger50hChineseSinging
Opencpop5hChineseSinging
PopBuTFy10h, 40hChinese, EnglishSinging
POPCS5hChineseSinging
VCTK44hEnglishSpeech
VocalSet10hOtherSinging

License

FreeSVC is released under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) license. This means:

  • The model can only be used for research and non-commercial purposes. Any commercial use is strictly prohibited.
  • Any derivative works must be shared under the same license.
  • Proper attribution must be given when using the model.

Users must also comply with the licenses of the original datasets used for training. Some datasets may have additional restrictions beyond CC BY-NC-SA 4.0. Ensure you review and adhere to their terms before using the model.

For full details, refer to the CC BY-NC-SA 4.0 License.

Citation

@INPROCEEDINGS{10890068,
  author={Ferreira, Alef Iury and Gris, Lucas Rafael and Da Rosa, Augusto and Oliveira, Frederico and Casanova, Edresson and Sousa, Rafael and Junior, Arnaldo and Soares, Anderson and Filho, Arlindo Galvão},
  booktitle={ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
  title={FreeSVC: Towards Zero-shot Multilingual Singing Voice Conversion}, 
  year={2025},
  volume={},
  number={},
  pages={1-5},
  keywords={Training;Source coding;Zero shot learning;Refining;Signal processing;Data models;Acoustics;Multilingual;Data mining;Speech synthesis;Singing Voice Conversion;Synthesis of Singing Voices;Cross-lingual and multilingual aspects in speech synthesis},
  doi={10.1109/ICASSP49660.2025.10890068}}

Sources

1 source
Hugging FacePrimaryVersion ab1387ccbe1ed5e44187fd0f06ea52a882917ebd
huggingface.co/alefiury/free-svc/tree/ab1387ccbe1ed5e44187fd0f06ea52a882917ebd

Verified Sep 5

Model artifacts

3 artifacts

G_00014_0225000.pth

pth · 822 MB · SHA-256 0a132e8cb765…4b1e · Hugging Face

Download

rmvpe.pt

pt · 351 MB · SHA-256 1d49bd662038…1115 · Hugging Face

Download

spin.ckpt

ckpt · 477 MB · SHA-256 08b2f5082bc4…f6ee · Hugging Face

Download

Source excerpts

2 excerpts
ReadmeSep 5huggingface.co/alefiury/free-svc

--- license: cc-by-nc-sa-4.0 language: - en - pt - es - zh - nl - fr - de - it - ja - pl pipeline_tag: audio-to-audio tags: - audio - voice - voice conversion - singing voice conversion - vc - svc - multilingual --- # FreeSVC: Zero-shot Multilingual Singing Voice Conversion **FreeSVC** is a promising multilingual zero-shot singing voice conversion model. It enables the conversion of singing voices across languages without the need for extensive language-specific training. [GitHub repository](https://github.com/freds0/free-svc). [Paper arXiv pre-print](https://arxiv.org/abs/2501.05586). ## Supported Languages | Language | ID | Status | Speech Data | Singing Data | |------------|-----|--------------|-------------|--------------| | Chinese | 0 | ✅ Full | 255h | 70h | | Dutch | 1 | ✅ Full | Part of CML | - | | English | 2 | ✅ Full | 921h | 47h | | French | 3 | ✅ Full | Part of CML | - | | German | 4 | ✅ Full | Part of CML | - | | Italian | 5 | ✅ Full | Part of CML | - | | Japanese | 6 | ✅ Full | 30h | - | | Other* | 7 | ⚠️ Partial | - | 10h | | Polish | 8 | ✅ Full | Part of CML | - | | Portuguese | 9 | ✅ Full | Part of CML | - | | Spanish | 10 | ✅ Full | Part of CML | - | *Note: The "Other" category is used for vocal techniques without content. ## Model Overview FreeSVC leverages an enhanced VITS architecture integrated with Speaker-invariant Clustering (SPIN) and the ECAPA2 speaker encoder. This combination effectively separates speaker characteristics from linguistic content, ensuring high-quality and natural-sounding voice conversions across multiple languages. ## Training Datasets FreeSVC was trained on a diverse set of speech and singing datasets covering multiple languages: | **Dataset** | **Hours** | **Language** | **Type** | |----------------------|------------|--------------|--------------| | AISHELL-1 | 170h | Chinese | Speech | | AISHELL-3 | 85h | Chinese | Speech | | CML-TTS | 3.1k | 7 Languages | Speech | | HiFiTTS | 292h | English | Speech | | JVS | 30h | Japanese | Speech | | LibriTTS-R | 585h | English | Speech | | NUS (NHSS) | 7h | English | Speech, Singing | | OpenSinger | 50h | Chinese | Singing | | Opencpop | 5h | Chinese | Singing | | PopBuTFy | 10h, 40h | Chinese, English | Singing | | POPCS | 5h | Chinese | Singing | | VCTK | 44h | English | Speech | | VocalSet | 10h | Other | Singing | ## License FreeSVC is released under th...

NoteSep 5huggingface.co/alefiury/free-svc

Source context: 95 downloads · 8 likes · Pipeline audio-to-audio · Repo alefiury/free-svc