FranceFrank
SKEV Project
FranceFrank is an experimental DiffSinger voicebank created by PRINTmov to explore cut-corner training solutions. With FranceFrank joining the 2Player Music project alongside Printto and Kaiz, the project has now been rebranded as SKEV.
FranceFrank DiffSinger dataset was recorded in Thai. The voicebank utilizes multiple public datasets for XLS (cross-language) support. Some of his samples are also included in Printto TH public dataset labeled as Pyao.
FranceFrank V2 supports more languages and improved quality.
| Main Language | Thai |
| Supported Languages | English, Thai, Japanese, French, Russian, Korean, Spanish, Chinese, Indonesian, and Filipino |
| Data Used |
Alex Floarea Bento Fuwari Chinoame Chiyu CSD (Relabeled by heta-tan) FranceFrank Kaiz Keiro Llane Crow Kone Hiro Lucy Roos M4Singer (Relabeled by nobodyP) Namine Criss Ofuton P Opencpop (Relabeled by Komisteng) PetitMillefeuille PJS (Relabeled by Utautautau) Project AI❤dol Lucy Roos Tanya Magicbeat TGM Corpus Toshio Sasagawa Zephyr |
| Vocoder | pc_tgm_hifigan |
The first version of FranceFrank. The voicebanks supports 3 languages.
The voicebank produces mellow male vocal.
| Languages | English, Japanese, and Thai |
| Data Used | TIGER, PJS, Ofuton P, and Printto TH |
FranceFrank Millefeuille Edition is a DiffSinger voicebank trained by UFR. The model is based on Pyao vocal in Printto TH Dataset (v24.08.05). This voicebank supports 12 languages with Millefeuille's XLS standard.
| Languages | Chinese, English, French, German, Italian, Japanese, Korean, Polish, Portuguese, Russian, Spanish, and Thai |
| Vocal Modes | Default |
| System | Multi-dictionary |
| Data Used | Millefeuille XLS Credits |
Please ensure that you read the README.txt file provided with the downloaded voicebanks before using them. It contains important instructions and guidelines that must be followed.