https://mistral.ai/news/voxtral
Mistral has unveiled Voxtral, an exciting new AI audio model that positions itself as a strong open-source competitor to Whisper, the reigning champion of speech recognition. With claims of outperforming Whisper by 50%, Voxtral is set to shake up the landscape of open-source speech technology.
Voxtral comes in two sizes: a 24B model for production-scale applications and a 3B variant for local use. Both models are released under the Apache 2.0 license, ensuring flexibility and accessibility.
Leave a Comment