Fact · Speech recognition
4.72times faster than real time
On an NVIDIA Jetson, the pretrained Whisper-small model had a real-time factor of 0.212, which is 4.72 times faster than real time, on 264 cleft lip and palate utterances.
Quote found word for word on the live source, last checked October 19, 2026
In the source's own words
“The pretrained Whisper-small baseline achieved an overall RTF of 0.212, corresponding to4.72×real-time processing”
Fairness Evaluation of Edge-AI Implementation for Cleft Lip and Palate Speech ASR, Susmita Bhattacharjee et al., arXiv, 2026, Section 3.1, Deployment Results.
Open the original- What it measures
- Inference of the zero-shot baseline, FP16 on the Jetson GPU with greedy decoding, over 264 evaluation utterances.
- What it does not show
- A single deployment on one edge board, with inference time only for the reported RTF. The speed depends on the Jetson model, which the paper does not name.
In the data
A row of Speech Recognition Speed: Real-Time Factor Data, as Bhattacharjee et al. 2026, pretrained: 5 times faster than real time.
- System
- Whisper-small, pretrained (zero-shot)
- Kind
- Open model
- Hardware
- NVIDIA Jetson (ARM CPU + CUDA GPU)
- Test set
- NMCPC cleft lip and palate speech, 264 utterances
- Year
- 2026