
xeon
@saymycodename
ML โข research @iit__mandi // 2xstartup
ID: 1452841814424055810
26-10-2021 03:37:55
1,1K Tweet
159 Followers
191 Following








Prime Intellect I built an env to test whether audio LLMs build prosodyโonly reasoning chains on MELD (multimodal emotion dataset). Models listen to an utterance (raw audio file) and then must output one sentence like: <impression> higher pitch, noticeable variation, moderate








