Follow
Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks. (arXiv:2309.07937v1 [eess.AS]) http://arxiv.org/abs/2309.07937
Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks. (arXiv:2309.07937v1 [eess.AS]) http://arxiv.org/abs/2309.07937