These tests measure performance in varying signal-to-noise conditions: the kinds of audio found in meeting rooms, contact centres, & phone calls. In other words, environments where enterprise speech applications actually operate. Cohere Transcribe ranked #1 across every metric:
@cohere
-
Transcribe surpasses IBM and NVIDIA speech models with 17.9 WER
By
–
Transcribe achieved a 17.9 WER – nearly 2 points ahead of IBM Granite Speech and 3.6 points ahead of NVIDIA’s Parakeet. Still Apache 2.0 and runs on your laptop. Enterprise performance developer ergonomics. Full results:
-
Transcribe tops OpenASR and far-field speech benchmarks
By
–
In March, Transcribe topped the OpenASR leaderboard for general-purpose speech recognition. Today, it leads a benchmark designed to go beyond and test robustness in real-world, far-field audio environments. Give it a try and share back what you build:
-
Cohere Transcribe, open-source ASR model, #1 on Hugging Face benchmark
By
–
Cohere Transcribe, our open-source speech recognition model, is #1 on the new @huggingface Far-Field ASR benchmark.
-
A 2023 article influences global AI policies
By
–
An article published three years ago influences policymakers worldwide regarding AI-related labor decisions. What happens when the gap between evidence and new policies widens? Our report from @Cohere_Labs examines these effects, in
-
Small AI model: 30B parameters, 3B active, open source
By
–
Small: 30 billion parameters, 3B active.
Efficient: Benchmarks reaching 33.4 on Artificial Analysis coding index, competitive among similarly sized models.
Open Source: Apache 2.0 license so developers can experiment, test and -
Cohere presents North Mini Code, open-source coding model
By
–
Introducing Cohere's first open-source coding model: North Mini Code
— Cohere (@cohere) 9 juin 2026
Small & efficient, designed for agentic performance and built for community input. pic.twitter.com/GYk5ORtysUIntroducing Cohere's first open-source coding model: North Mini Code. Small and efficient, designed for agentic performance and built for community feedback.
-
Cohere & Hugging Face Webinar: Future of Far-Field ASR & Real-World Evaluation
By
–
Want to hear about where ASR is headed? Check out @HuggingFace
's webinar about their new Far-Field ASR Leaderboard with @shinjiw_at_cmu and our own @Julianfmack on Thursday, June 11th. We'll be chatting about Cohere Transcribe and how to evaluate ASR systems in the real world. -
Last Chance to Register for Build Small Hackathon & Model Suggestions
By
–
Registration closes tomorrow, Wednesday, June 3rd. Register here: https://
huggingface.co/spaces/build-s
mall-hackathon/registration
… If you're looking for a model to use to tackle this hackathon, check out Transcribe & Tiny Aya (led by @alexrs95
). Both models fit the parameters of the challenge. -
Command A+ Translation Model Outperforms on WMT24++ Benchmark
By
–
The improvements run wide. Across all major European languages, Command A+ consistently pulls ahead of competitors on WMT24++ (xCOMET-XL): +2.4 pts in French +1.9 pts in Spanish +0.9 pts in German Higher translation quality means fewer corrections, stronger retrieval,