Wonke amathuluzi e-AI
Ukwenziwa kwenkulumo nge-AI
Lapha kuqoqwe imikhiqizo ye-AI edumile yokwenziwa kwenkulumo, ehlanganisa ukudala, ukucubungula nokwandisa ukusebenza kahle.
Ming-3.0Ukwenziwa kwenkulumo nge-AII-Ming-3.0 iwuchungechunge lwamamodeli ezwi olukhishwe njenge-open source yi-Ant Group's Bailin, oluhlanganisa imisebenzi emithathu: ukuhlanganisa izwi, ukuqonda nomsindo nengxoxo, kanye nokubona izwi. Lethula amamodeli amahlanu: uchungechunge lwe-Ming-3.0-tts lusekela “Imodi Yomqondisi” yokulawula ngokuningiliziwe imizwa, ijubane...00
Step Audio 3Ukwenziwa kwenkulumo nge-AII-StepAudio 3 iwuchungechunge lwamamodeli amakhulu ezwi olwethulwe yi-Jieyue Xingchen, oluhlanganisa amamodeli amahlanu: i-Realtime, ASR, TTS, Gen ne-Music. Phakathi kwawo, ukunemba kokucabanga ngezwi kwe-Realtime kungu-99.7%, kanti izinga lamaphutha amagama le-ASR lingu-1.7%...00
dots.ttsUkwenziwa kwenkulumo nge-AII-dots.tts iyimodeli eyisisekelo yokwenziwa kwenkulumo ye-autoregressive eqhubekayo ngokuphelele, enamapharamitha ayizigidigidi ezi-2, ekhishwe ngomthombo ovulekile ngokubambisana yiqembu le-Xiaohongshu dots kanye ne-X-LANCE Laboratory yase-Shanghai Jiao Tong University. Imodeli ikhiqiza umsindo we-48kHz ngamaqoqo ngokuqondile endaweni efihlekile eqhubekayo, futhi...00
IndexTTS-2.5Ukwenziwa kwenkulumo nge-AII-IndexTTS-2.5 iyimodeli yokukopisha izwi esezingeni lezimboni ye-zero-shot, ekhishwe yi-Bilibili njengomthombo ovulekile. Inamapharamitha angu-0.8B kuphela, futhi isekela ukudluliselwa kwezwi phakathi kwezilimi ezinhlanu: isiShayina, isiNgisi, isiJapane, iSpanishi nesi-Arabhu.00Wonke amathuluzi akulesi sigaba ayaboniswa.