k
keynews.ai
keynews.ai
FrontierThe story, in brief

Best Open Speech Recognition (ASR) Models in 2026: WER, Languages, Latency, and License Compared

Whisper's reign is over. Four open ASR models now trade wins within 1 WER point—here's how to actually pick between them.

Reporting by MarkTechPost 1 min brief
Illustration of a transparent lens revealing connected networks across layers of paper.
Exploring the next frontier of AI research.AI illustration by KeyNews
The KeyNews take

Why it matters

Speech recognition has shifted from single-model dominance to a competitive open-weight landscape. Leaders and builders need updated benchmarks beyond leaderboard rankings to choose the right ASR for production, especially as latency, language coverage, and licensing now separate winners.

The key facts

4 to know

  1. Cohere Transcribe, IBM Granite Speech 4.1, ARK-ASR, and MOSS-Transcribe all within <1 WER point on Hugging Face Open ASR Leaderboard

  2. 16 open-weight models compared across metrics: word error rate (WER), language coverage, streaming latency, license

  3. Published averages cannot be subtracted directly—benchmarks require contextual interpretation

  4. Speech recognition market shifted from Whisper monoculture to multi-model competition in 2026

Go to the source

MarkTechPostmarktechpost.com

Publisher excerpt: Open speech recognition stopped being a Whisper monoculture in 2026. Cohere Transcribe, IBM Granite Speech 4.1, ARK-ASR and MOSS-Transcribe are now separated by less than one WER point on the Hugging Face Open ASR Leaderboard — which means rank no longer decides anything. This roundup compares 16…
Read original report
Back to today's editionMore frontier news

The wider picture

View all
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier01

Alibaba Unveils Zhenwu V900 — and Plans Qwen Models With Up to 10 Trillion Parameters

Alibaba is advancing on two fronts simultaneously: announcing a custom AI accelerator (Zhenwu V900) and committing to massive model scale (10T parameters for future Qwen releases). For practitioners, this matters as a credible third-party capability play outside the US-China licensing squeeze; for enthusiasts, it's a significant lab-race signal about training compute and parameter scaling as competitive levers.

TechRepublic
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier02

Kyutai Releases Voice of Reason: A Speech-Native Model that Solves Spoken Math with Reinforcement Learning

A new capability frontier: models that reason directly in speech without transcription bottlenecks. This changes how we think about multimodal reasoning and what's possible with open-weight releases at scale.

MarkTechPost
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Frontier03

Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war

Frontier labs are shipping upgraded reasoning and multimodal models in rapid succession, signaling acceleration in the capability race. Simultaneous price cuts reshape AI economics for practitioners.

Simon Willison