all AI news
Meta's Open-Source Massively Multilingual Speech AI Handles over 1,100 Languages
InfoQ - AI, ML & Data Engineering www.infoq.com
Meta AI open-sourced the Massively Multilingual Speech (MMS) model, which supports automatic speech recognition (ASR) and text-to-speech synthesis (TTS) in over 1,100 languages and language identification (LID) in over 4,000 languages. MMS can outperform existing models and covers nearly 10x the number of languages.
By Anthony Alfordai anthony asr automatic speech recognition deep learning identification language languages meta meta ai ml & data engineering mms multilingual natural language processing neural networks recognition speech speech ai speech recognition synthesis text text-to-speech tts