PulseAugur
LIVE 13:11:00
research · [1 source] ·
0
research

Mistral's Voxtral ASR models outperform OpenAI Whisper on benchmarks

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 1 source

Mistral AI has released Voxtral, a new state-of-the-art automatic speech recognition (ASR) model. Available in 3 billion and 24 billion parameter sizes, Voxtral has demonstrated superior performance compared to OpenAI's Whisper large-v3 model. This release signifies an advancement in open-source ASR technology. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

RANK_REASON Release of a new model from a well-known AI lab (Mistral AI) with benchmark comparisons.

Read on Smol AINews →

COVERAGE [1]

  1. Smol AINews TIER_1 ·

    Voxtral - Mistral's SOTA ASR model in 3B (mini) and 24B ("small") sizes beats OpenAI Whisper large-v3

    **Mistral** surprises with the release of **Voxtral**, a transcription model outperforming **Whisper large-v3**, **GPT-4o mini Transcribe**, and **Gemini 2.5 Flash**. Voxtral models (3B and 24B) support **32k token context length**, handle audios up to **30-40 minutes**, offer bu…

RELATED TOPICS