@MistralAI: Introducing Voxtral Transcribe 2, next-gen speech-to-text models by @MistralAI. State-of-the-art tra...
Introducing Voxtral Transcribe 2, next-gen speech-to-text models by @MistralAI. State-of-the-art transcription, speaker diarization, sub-200ms real-time latency. Details in 🧵 https://t.co/0IeiJOpiAZ