Meta Launches Omnilingual ASR Supporting Over 1,600 Languages
We’re introducing Meta Omnilingual Automatic Speech Recognition, a suite of models providing automatic speech recognition capabilities for over 1,600 languages.
Read the full articleYou might also wanna read
Meta Expands AI Translation Tool for Instagram and Facebook Reels with Voice and Lip-Sync Features
You can even have Meta AI match the movement of your lips to the translated audio.
The Verge·11mo ago
Microsoft Launches MAI-Transcribe-1: Multilingual Speech-to-Text Model for Production Use
Microsoft AI is pioneering the future of what AI can do and what technology can be.
Product Hunt·1mo ago
Why Big ASR Models Struggle with Low-Resource African Languages
Extending large ASR models to low-resource African languages isn't as simple as it seems. Linguistic relatedness might not be the silver bul
Breaking Barriers: New Spanish Dataset Tackles ASR Challenges in Neurological Speech
S-DiverSe introduces a groundbreaking dataset for Spanish speech affected by neurological conditions, highlighting critical gaps in current
Cohere releases open-source 2B parameter Arabic ASR model with dialect and code-switching support
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Huawei's Modelers.cn platform adds Meta's Icelandic TTS model for low-resource language support
Meta's MMS Icelandic TTS on Ascend NPUs is a genuinely useful port — low-resource Nordic languages getting native-on-chip inference is the k
aichina.news·13d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.