Fact · Speech recognition
9.85percent word error rate
NVIDIA Canary 1B Flash had a word error rate of 9.85 percent on the GigaSpeech test set in the Open ASR Leaderboard table.
Quote found word for word on the live source, last checked October 19, 2026
In the source's own words
“| **Version** | **Model** | **RTFx** | **AMI** | **GigaSpeech** | **LS Clean** | **LS Other** | **Earnings22** | **SPGISpech** | **Tedlium** | **Voxpopuli** | ... | nemo-main | canary-1b-flash | 1045.75 | 13.11 | 9.85 | 1.48 | 2.87 | 12.79 | 1.95 | 3.12 | 5.63 |”
canary-1b-flash model card (raw README), NVIDIA, Hugging Face (NVIDIA model card), n.d., Open ASR Leaderboard table, GigaSpeech column.
Open the original- What it measures
- The model card's Hugging Face Open ASR Leaderboard table gives the WER for each dataset in the leaderboard's English set.
- What it does not show
- A vendor-run score on the leaderboard's English datasets, with the leaderboard's text normalization. Compare only with systems scored the same way.
In the data
A row of Speech Recognition Accuracy: Word Error Rates, as Canary 1B Flash, GigaSpeech English: 9.85 percent.
- System
- NVIDIA Canary 1B Flash
- Kind
- Open model
- Test set
- GigaSpeech
- Language
- English
- Speech
- Mixed benchmark