ModelsAgree
← All leaderboards

NVIDIA Canary-Qwen 2.5B

What ChatGPT, Claude, Gemini & Grok actually say · July 2026

Visit nvidia.com

The verdict

NVIDIA Canary-Qwen 2.5B appears in 1 AI-ranked category — best position #3 for open-source speech-to-text model.

#3🗣 Best open-source speech-to-text model3/4 models · updated 2026-07-15
GPT #5Claude #4Gemini Grok #1

Tops or near-tops Hugging Face Open ASR Leaderboard with ~5.63% avg WER on English benchmarks via strong Conformer + Qwen LLM decoder hybrid (SALM architecture); excellent accuracy for typical practitioner use in clean-to-moderate noisy English audio; strong community/HF support and NVIDIA tooling for deployment.

Claude Took the top WER spot on the Open ASR Leaderboard at release with a hybrid ASR+LLM design that also enables post-transcription tasks (summarization, Q&A), CC-BY licensed and commercially usable — near-tie with Parakeet, which wins above it only on throughput per dollar for bulk transcription.

GPT Exceptional English accuracy, punctuation, capitalization, hallucination robustness, and optional transcript summarization or question answering

Where NVIDIA Canary-Qwen 2.5B falls short, per the models

  • GPT It is English-only, relatively large, NeMo-dependent, and optimized around audio segments no longer than roughly 40 seconds
  • Claude English-only, which disqualifies it for the many practitioners who need multilingual support (its multilingual Canary 1B sibling covers fewer languages at lower accuracy).
  • Grok Higher latency/compute needs than lighter CTC/TDT models; not ideal for real-time streaming or very low-resource/edge devices without optimization.

Top alternatives per the models: OpenAI Whisper · NVIDIA Parakeet TDT · IBM Granite Speech · Qwen3-ASR

Embed your ranking badge

NVIDIA Canary-Qwen 2.5B ranks #3 for best open-source speech-to-text model by AI-model consensus. Put the badge in your README, docs or site — it updates automatically as the models re-rank.

NVIDIA Canary-Qwen 2.5B — ranked #3 for Best open-source speech-to-text model by AI models on ModelsAgree
Markdown (README)
[![NVIDIA Canary-Qwen 2.5B — ranked #3 for Best open-source speech-to-text model by AI models on ModelsAgree](https://modelsagree.com/badge/nvidia-canary-qwen-2-5b.svg)](https://modelsagree.com/best/best-open-source-speech-to-text-model?utm_source=badge&utm_medium=embed&utm_campaign=badge-nvidia-canary-qwen-2-5b)
HTML
<a href="https://modelsagree.com/best/best-open-source-speech-to-text-model?utm_source=badge&utm_medium=embed&utm_campaign=badge-nvidia-canary-qwen-2-5b"><img src="https://modelsagree.com/badge/nvidia-canary-qwen-2-5b.svg" alt="NVIDIA Canary-Qwen 2.5B — ranked #3 for Best open-source speech-to-text model by AI models on ModelsAgree" height="28"></a>

Rankings are computed from what the models answer, re-polled weekly · raw reasoning shown verbatim · methodology