This project implements a Speech-to-Speech Translator, which captures spoken input, transcribes it into text, translates it into a target language, and converts the translated text back into speech.
A speech synthesizer is used to produce audio. It can translate speech from any of 101 languages, although the results are available in only 36 languages so far. The system can also perform other ...
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation ...
cropped view of translator ... languages. “Meta has done a great job having a breadth of different things they support, like text-to-speech, speech-to-text, even automatic speech recognition ...