VITS ສຽງເປັນຂໍ້ຄວາມ
The end-to-end TTS architecture that combines a variational autoencoder, normalizing flows, and adversarial training.
ວາງຂໍ້ຄວາມຂອງທ່ານໄວ້ໃນແທັກ SSML ເພື່ອຄວບຄຸມຢ່າງລະອຽດ:
<speak><prosody rate="slow">Slow speech</prosody></speak>
ແທັກທີ່ຕົວແບບທີ່ໄດ້ເລືອກເຂົ້າໃຈ — ກົດເພື່ອປ່ອຍພວກມັນລົງໃນຂໍ້ຄວາມຂອງທ່ານບ່ອນທີ່ມັນເກີດຂຶ້ນ:
ແບບນີ້ອ່ານຂໍ້ຄວາມປົກກະຕິ, ສະນັ້ນແທັກໃນແຖບຈະບໍ່ຖືກລະບຸໄວ້. ສຳລັບຄວາມຮູ້ສຶກທີ່ອີງໃສ່ແທັກ, ປ່ຽນໄປຫາແບບທີ່ສະແດງອອກຄື Orpheus ຫຼື Bark.
ຕັ້ງຄ່າການອອກສຽງແບບສ່ວນຕົວ (ຄໍາ = ການອອກສຽງ):
ກ່ຽວກັບ VITS
VITS — Variational Inference with adversarial learning for end-to-end Text-to-Speech — was introduced by Jaehyeon Kim and collaborators in 2021 and became a foundational architecture for modern neural speech. Rather than the older two-stage pipeline, it synthesizes audio in a single parallel end-to-end pass, pairing a variational autoencoder with normalizing flows and a GAN-style adversarial training process to lift naturalness. At about 25M parameters and trained on ~585 hours, it produces natural prosody at fast inference speeds and supports multiple speakers. It serves as a solid general-purpose, free baseline and underpins many later models such as Piper and MeloTTS.
ດີທີ່ສຸດ ສຳ ລັບ: General-purpose text-to-speech with natural prosody
ຄົ້ນຫາທັງໝົດ VITS ສຽງເບິ່ງຢ່າງໄວວາ
- ຜູ້ພັດທະນາ
- Jaehyeon Kim et al.
- ໃບອະນຸຍາດ
- MIT
- ສັດ
- free
- ໄວ
- fast
- ການປິດສຽງ
- ບໍ່
- ພາສາ
- English, German, Spanish, French, Portuguese, Dutch, Finnish, Hungarian, Bulgarian, Japanese, Polish
- ຕົວອັກສອນສູງສຸດ
- 2000