註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

SpaceX Super Intelligence
@SpaceXSI
加入 May 2023
6 正在關注    2.1M 粉絲
We built our entire voice stack in-house, training our VAD, tokenizer, and audio models from scratch. In blind head-to-head human evaluations against OpenAI, Grok is consistently rated as the preferred model across axes such as pronunciation, accent, and prosody.
顯示更多
0
3
414
28
轉發到社區