#automatic speech recognition

Mistral AI launches Voxtral, cutting-edge open-weight speech recognition models that integrate transcription and language understanding with support for long audio contexts and multiple languages.

NVIDIA's Joey Conway discusses groundbreaking open-source AI models Llama Nemotron Ultra and Parakeet, highlighting innovations in reasoning control, data curation, and rapid speech recognition.

NVIDIA has released Parakeet TDT 0.6B, an open-source ASR model that transcribes an hour of audio in just one second while achieving top accuracy benchmarks, setting a new industry standard.