model detail

Where this model stands against the best model in each language at Q8_0, its speed on an AMD Ryzen 4750U laptop, and what the card says. Add a second model to compare them head to head.

model whisper-small
AMD 4750U GPU12.1×
AMD 4750U CPU3.4×
Q8_0 size0.25 GB
frontier · AMD 4750U GPU7 of 39

verdict: Never first, and outside the leader's 95% CI in all 39 languages. Weakest relative to the field in Japanese (CER) (5.5× the leader's error), Latvian (5.5×), and Hindi (5.4×). Faster than realtime on the AMD 4750U GPU (12.1×) and AMD 4750U CPU (3.4×).

license: Apache-2.0 · card languages: 99 · translatelang detecttimestamps (segment)

standing by language · 39 benchmarked

Each bar compares this model with the best other model in that language, on a log scale: left of center it is ahead, right of center behind, and the other model is named on the row. The two error rates use the legend colors: this model first, the other model second. Faded bars are ties, where the 95% confidence intervals overlap. Sorted strongest standing first. Hover a row for full details.

whisper-small error best other model error tie: the 95% CIs overlap

speed · all 19 models on the AMD 4750U GPU

× realtime, log scale. Left of the realtime marker, transcribing takes longer than the recording. Hover a dot for the model.

compare with

whisper-large-v3same familywhisper-large-v3-turbosame familywhisper-mediumsame familyQwen3-ASR-1.7Bahead of it in 29 of 29 shared languagesFun-ASR-MLT-Nano-2512closest coverage, 29 languages in common