This bundle prepares one RVC v2, 40 kHz, F0-guided multi-speaker base model from: - AISHELL/AISHELL-3 on Hugging Face; - badayvedat/VCTK on Hugging Face; - the official JVS Google Drive archive; - hfmwhisper110spk.zip in Rvcmodel/gbs.
Dataset Card
This bundle prepares one RVC v2, 40 kHz, F0-guided multi-speaker base model from: - AISHELL/AISHELL-3 on Hugging Face; - badayvedat/VCTK on Hugging Face; - the official JVS Google Drive archive; - hfmwhisper110spk.zip in Rvcmodel/gbs. The HFM package contains 13,303 mono 48 kHz/16-bit WAV files from 110 speakers, totaling 19.889 hours. Its SHA-256 is cfc382e9b9b176a3c9d854bbcd0edaf8647d3beaba13ca6ea5f84abdb899a3db. The script pins upstream RVC commit 81eed5e8f68b6bed1789f682fe78cdd324495afc. That revision supports multi-speaker manifests but caps the helper at speaker ID 109, so the bootstrap raises only that manifest-validation limit. The model embedding size is generated from the actual…
Excerpt from the card by Rvc Model, licensed other.
Details
- Repository
- Rvcmodel/gbs
- Publisher
- Rvc Model
- Task category
- Audio to audio
- Tags
- Not stated by the source
- Size category
- Not stated by the source
- Languages
- zh, en, ja
- Revision
- 2da222c0ee3f9877f9e6d6a7b34f7f8d8a2d5c19
- Last updated
- 2026-09-28
Files
8 files, 2.2 GB in total.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| hfm_whisper_110spk.zip | Data | 2.2 GB | cfc382e9b9b1 |
| README.md | Documentation | 2.5 KB | — |
| pretrain_tools/README.md | Documentation | 3.2 KB | — |
| pretrain_tools/bootstrap_rvc_pretrain.sh | Other | 7.9 KB | — |
| pretrain_tools/build_multilingual_dataset.py | Other | 17.2 KB | — |
| pretrain_tools/finalize_rvc_experiment.py | Other | 4.7 KB | — |
| pretrain_tools/package_hfm_whisper.py | Other | 6.1 KB | — |
| .gitattributes | Repository | 2.5 KB | — |
License and Download
- License
- other
- Access
- No access gate
Released by Rvc Model through its official repository on Hugging Face.