Darwin TTS ТТС
A Qwen3-TTS variant whose talker FFN weights are blended from the Qwen3 language model for sharper cross-lingual cloning.
Тодорхой хяналтын тулд SSML тэмдгээр текстээ буулгах:
<speak><prosody rate="slow">Slow speech</prosody></speak>
Бүх
Энэ загвар нь энгийн утга уншдаг, тиймээс доторх тэмдгийг үл тоомсорлодог. Тэг- суурилсан сэтгэл хөдлөл, Orpheus эсвэл Bark- шиг илэрхийлэх загвар руу шилжинэ.
Өөрийн дуудлагыг тодорхойлох (үг = дуудлага):
Тодорхойлолт Darwin TTS
Darwin-TTS-1.7B-Cross by FINAL-Bench is a research variant of Qwen3-TTS-1.7B with an unusual construction: 84 of its talker-FFN tensors (about 8.6% of them) are blended at a 3% ratio with the matching tensors from Qwen3-1.7B-Base, all without any retraining. The result is a model that produces noticeably crisper cross-lingual voice cloning across Korean, English, Japanese, and Chinese — its four core languages. It operates in zero-shot voice-clone mode, needing only about three seconds of reference audio to capture a speaker. Darwin is best suited to transferring a single reference voice across those four languages, for example dubbing or multilingual narration with consistent speaker identity.
Хамгийн сайн: Cross-lingual voice cloning between English / Korean / Japanese / Chinese with a single reference voice
Бүхнийг харах Darwin TTS дуунуудНүүр хуудас
- Хөгжүүлэгч
- FINAL-Bench
- Лиценз
- Apache 2.0
- Үхрийн
- standard
- Хурд
- medium
- Дууны дугуй
- Тийм
- Хэл
- English, Korean, Japanese, Chinese
- Хамгийн их үсэг
- 2000