Meta returns to open source AI with Omnilingual ASR models that can transcribe 1,600+ languages natively

Meta has just released a new multilingual automatic speech recognition (ASR) system supporting 1,600+ languages — dwarfing ...

aiOla unveils Drax, an open-source speech model with state-of-the-art accuracy and up to 5× faster than models from direct competitors

PRNewswire/ -- aiOla, a voice-AI lab advancing speech recognition technology, is announcing today Drax, an open-source AI model that brings flow-matching-based generative methods to speech. By ...
Nature

Striving for open-source and equitable speech-to-speech translation

• Billions of people around the world regularly communicate online in languages other than their own. • This has created huge demand for artificial intelligence (AI) models that can translate both ...
India Today on MSN

Meta claims its new open source AI can understand more than 1600 languages, is superintelligence next?

Meta has introduced Omnilingual ASR, a new open-source AI system which can recognise more than 1,600 languages, including 500 previously unsupported.