Vendor page
canary-qwen-2.5b model card
NVIDIA, Hugging Face, n.d.
Read the originalRead on October 17, 2026
- What it is
- NVIDIA's model card for Canary-Qwen-2.5B, a speech recognition model that pairs a speech encoder with a language-model decoder. The card states that the model is ready for commercial use under CC-BY-4.0.
- How much weight it carries
- Written by the model's publisher, so it is authoritative for the license and the intended use. Its accuracy figure is taken from the Open ASR Leaderboard paper, which is independent of NVIDIA.
Facts taken from this source
- NVIDIA's Canary-Qwen model maps the audio encoder's output into the language model's embedding space through a linear projection.
“The audio encoder computes audio representation that is mapped to the LLM embedding space via a linear projection” (Model Architecture)
- NVIDIA says Canary-Qwen-2.5B is ready for commercial use and is released under the CC-BY-4.0 license.
“This model is ready for commercial use. License/Terms of Use: Canary-Qwen-2.5B is released under the CC-BY-4.0 license.” (Intended use and License/Terms of Use)