Model Releases
Can an STT model make sense of a 135 year old recording? I tested @MistralAI new Voxtral transcription model on a noisy French phonograph re…
Can an STT model make sense of a 135 year old recording? I tested @MistralAI new Voxtral transcription model on a noisy French phonograph recording of Gustave Eiffel from 1891. It matched 100 of 107 w
Can an STT model make sense of a 135 year old recording? I tested @MistralAI new Voxtral transcription model on a noisy French phonograph recording of Gustave Eiffel from 1891. It matched 100 of 107 words in INA’s published excerpts (6.5% WER), while transcribing 75 additional words omitted from the reference. It handled Eiffel’s dictation well but struggled with proper names and some guest dialogue. A fascinating test of modern speech recognition on audio from 1891. Media Introducing Voxtral 3: state-of-the-art Transcribe and Speech models powering Mistral’s new voice agents API. 🧵
Source: Mistral AI (X) | 2026-10-20