SeamlessM4T
FacebookINRIAUniversity of California (UC) BerkeleyTranslationSpeech synthesisSpeech recognition (ASR)Speech-to-textSpeech-to-speechOpen weights
SeamlessM4T is a translation model from Facebook,INRIA,University of California (UC) Berkeley released in 2023 with 2300000000.0 parameters.
About SeamlessM4T
Large-scale automatic speech translation systems today lack key features that help machine-mediated communication feel seamless when compared to human-to-human dialogue. In this work, we introduce a family of models that enable end-to-end expressive
Details
- Provider
- Facebook,INRIA,University of California (UC) Berkeley
- Task
- Translation,Speech synthesis,Speech recognition (ASR),Speech-to-text,Speech-to-speech
- Parameters
- 2300000000.0
- Released
- 2023-12-08
- Open weights
- Yes