Xingjian Shi retweeted
Boson AI's new audio generation model is out: emotionally expressive voice, long form audio, multi-speaker cloning, directable audio (e.g. music, laughter), trained on 10M+ hours of audio, and best of all, open source. boson.ai/blog/higgs-audio-v2 - @boson_ai @sxjscience @mli65
Xingjian Shi retweeted
We're hiring for Boson AI. Talk to @sxjscience at #ACL2023 if you want to work on language alignment, finetuning, infrastructure and serving, statistical modeling, optimization, model evaluation, and data.
Xingjian Shi retweeted
This paper will appear at #ICLR2023, with amazing collaborators Z. Liu, Z. Tang, @sxjscience, @astonzhangAZ, @mli65, A. Shrivastava. Code is available at github.com/lzcemma/LeMDA/.


