Official documentation
canary-qwen-2.5b model card (raw README)
NVIDIA, Hugging Face (NVIDIA model card), 2025
Read the originalRead on October 19, 2026
- What it is
- NVIDIA's model card for Canary-Qwen 2.5B, read from its raw README. It gives English WER on the Open ASR Leaderboard datasets, and WER on LibriSpeech test-clean with added white noise at four signal-to-noise ratios.
- How much weight it carries
- Self-reported by NVIDIA, the model developer. The card uses its own text normalization and decoding, so its figures are not directly comparable with other vendors' full-transcript scores. Compare only within the same test set.
Facts taken from this source
- NVIDIA Canary Qwen 2.5B had a word error rate of 10.18 percent on the AMI meetings test set in the Open ASR Leaderboard table.
“| **Version** | **Model** | **RTFx** | **Mean** | **AMI** | **GigaSpeech** | **LS Clean** | **LS Other** | **Earnings22** | **SPGISpech** | **Tedlium** | **Voxpopuli** | ... | 2.5.0 | Canary-Qwen-2.5B | 418 | 5.63 | 10.18 | 9.41 | 1.60 | 3.10 | 10.42 | 1.90 | 2.72 | 5.66 |” (Open ASR Leaderboard table, AMI meetings column)
- NVIDIA Canary Qwen 2.5B had a word error rate of 10.42 percent on the Earnings-22 test set in the Open ASR Leaderboard table.
“| **Version** | **Model** | **RTFx** | **Mean** | **AMI** | **GigaSpeech** | **LS Clean** | **LS Other** | **Earnings22** | **SPGISpech** | **Tedlium** | **Voxpopuli** | ... | 2.5.0 | Canary-Qwen-2.5B | 418 | 5.63 | 10.18 | 9.41 | 1.60 | 3.10 | 10.42 | 1.90 | 2.72 | 5.66 |” (Open ASR Leaderboard table, Earnings-22 column)
- NVIDIA Canary Qwen 2.5B had a word error rate of 9.41 percent on the GigaSpeech test set in the Open ASR Leaderboard table.
“| **Version** | **Model** | **RTFx** | **Mean** | **AMI** | **GigaSpeech** | **LS Clean** | **LS Other** | **Earnings22** | **SPGISpech** | **Tedlium** | **Voxpopuli** | ... | 2.5.0 | Canary-Qwen-2.5B | 418 | 5.63 | 10.18 | 9.41 | 1.60 | 3.10 | 10.42 | 1.90 | 2.72 | 5.66 |” (Open ASR Leaderboard table, GigaSpeech column)
- NVIDIA Canary Qwen 2.5B had a word error rate of 1.60 percent on the LibriSpeech test-clean test set in the Open ASR Leaderboard table.
“| **Version** | **Model** | **RTFx** | **Mean** | **AMI** | **GigaSpeech** | **LS Clean** | **LS Other** | **Earnings22** | **SPGISpech** | **Tedlium** | **Voxpopuli** | ... | 2.5.0 | Canary-Qwen-2.5B | 418 | 5.63 | 10.18 | 9.41 | 1.60 | 3.10 | 10.42 | 1.90 | 2.72 | 5.66 |” (Open ASR Leaderboard table, LibriSpeech test-clean column)
- NVIDIA Canary Qwen 2.5B had a word error rate of 3.10 percent on the LibriSpeech test-other test set in the Open ASR Leaderboard table.
“| **Version** | **Model** | **RTFx** | **Mean** | **AMI** | **GigaSpeech** | **LS Clean** | **LS Other** | **Earnings22** | **SPGISpech** | **Tedlium** | **Voxpopuli** | ... | 2.5.0 | Canary-Qwen-2.5B | 418 | 5.63 | 10.18 | 9.41 | 1.60 | 3.10 | 10.42 | 1.90 | 2.72 | 5.66 |” (Open ASR Leaderboard table, LibriSpeech test-other column)
- NVIDIA Canary Qwen 2.5B had a word error rate of 1.90 percent on the SPGI Speech test set in the Open ASR Leaderboard table.
“| **Version** | **Model** | **RTFx** | **Mean** | **AMI** | **GigaSpeech** | **LS Clean** | **LS Other** | **Earnings22** | **SPGISpech** | **Tedlium** | **Voxpopuli** | ... | 2.5.0 | Canary-Qwen-2.5B | 418 | 5.63 | 10.18 | 9.41 | 1.60 | 3.10 | 10.42 | 1.90 | 2.72 | 5.66 |” (Open ASR Leaderboard table, SPGI Speech column)
- NVIDIA Canary Qwen 2.5B had a word error rate of 2.72 percent on the TED-LIUM test set in the Open ASR Leaderboard table.
“| **Version** | **Model** | **RTFx** | **Mean** | **AMI** | **GigaSpeech** | **LS Clean** | **LS Other** | **Earnings22** | **SPGISpech** | **Tedlium** | **Voxpopuli** | ... | 2.5.0 | Canary-Qwen-2.5B | 418 | 5.63 | 10.18 | 9.41 | 1.60 | 3.10 | 10.42 | 1.90 | 2.72 | 5.66 |” (Open ASR Leaderboard table, TED-LIUM column)
- NVIDIA Canary Qwen 2.5B had a word error rate of 5.66 percent on the VoxPopuli test set in the Open ASR Leaderboard table.
“| **Version** | **Model** | **RTFx** | **Mean** | **AMI** | **GigaSpeech** | **LS Clean** | **LS Other** | **Earnings22** | **SPGISpech** | **Tedlium** | **Voxpopuli** | ... | 2.5.0 | Canary-Qwen-2.5B | 418 | 5.63 | 10.18 | 9.41 | 1.60 | 3.10 | 10.42 | 1.90 | 2.72 | 5.66 |” (Open ASR Leaderboard table, VoxPopuli column)
- NVIDIA Canary Qwen 2.5B had a word error rate of 9.83 percent on LibriSpeech test-clean with added white noise at 0 dB SNR.
“WER on [Librispeech Test Clean](https://www.openslr.org/12) at different SNR (signal to noise ratio) levels of additive white noise | **Version** | **Model** | **SNR 10** | **SNR 5** | **SNR 0** | **SNR -5** | ... | 2.5.0 | Canary-Qwen-2.5B | 2.41% | 4.08% | 9.83% | 30.60% |” (White-noise table, SNR 0 dB column)
- NVIDIA Canary Qwen 2.5B had a word error rate of 2.41 percent on LibriSpeech test-clean with added white noise at 10 dB SNR.
“WER on [Librispeech Test Clean](https://www.openslr.org/12) at different SNR (signal to noise ratio) levels of additive white noise | **Version** | **Model** | **SNR 10** | **SNR 5** | **SNR 0** | **SNR -5** | ... | 2.5.0 | Canary-Qwen-2.5B | 2.41% | 4.08% | 9.83% | 30.60% |” (White-noise table, SNR 10 dB column)
- NVIDIA Canary Qwen 2.5B had a word error rate of 4.08 percent on LibriSpeech test-clean with added white noise at 5 dB SNR.
“WER on [Librispeech Test Clean](https://www.openslr.org/12) at different SNR (signal to noise ratio) levels of additive white noise | **Version** | **Model** | **SNR 10** | **SNR 5** | **SNR 0** | **SNR -5** | ... | 2.5.0 | Canary-Qwen-2.5B | 2.41% | 4.08% | 9.83% | 30.60% |” (White-noise table, SNR 5 dB column)
- NVIDIA Canary Qwen 2.5B had a word error rate of 30.60 percent on LibriSpeech test-clean with added white noise at -5 dB SNR.
“WER on [Librispeech Test Clean](https://www.openslr.org/12) at different SNR (signal to noise ratio) levels of additive white noise | **Version** | **Model** | **SNR 10** | **SNR 5** | **SNR 0** | **SNR -5** | ... | 2.5.0 | Canary-Qwen-2.5B | 2.41% | 4.08% | 9.83% | 30.60% |” (White-noise table, SNR -5 dB column)