Fact · Speech recognition
10.62percent
In the formatted accuracy of on-device speech recognition: punctuation and capitals counted dataset, the 6 published figures for “Apple SpeechTranscriber” have a median of 10.62 percent, ranging from 10.34 to 100.
Calculated from 6 data points on October 19, 2026
- What it measures
- Each figure is one row of the dataset: a published measurement for a stated group, traced to its source. The median is the middle value of the 6 figures for this group.
- How it is calculated
- Median of 6 values (10.34, 10.43, 10.55, 10.68, 11.1, 100) = 10.62.
- What it does not show
- FLEURS sentences are read aloud from Wikipedia, with the source's punctuation; optional commas and style choices count as errors for every engine alike, so compare engines within a language rather than reading the number as the editing a person needs.
A statistic of the dataset Dictation Punctuation and Capitalization Accuracy, calculated by code from its published rows.
Calculated from
- In our October 2026 benchmark, counting punctuation and capital letters as a reader sees them, Apple SpeechTranscriber's text differed from the written German sentences by 10.55 errors per 100 tokens, against 6.87 for the words alone.
- In our October 2026 benchmark, counting punctuation and capital letters as a reader sees them, Apple SpeechTranscriber's text differed from the written English sentences by 11.10 errors per 100 tokens, against 6.73 for the words alone.
- In our October 2026 benchmark, counting punctuation and capital letters as a reader sees them, Apple SpeechTranscriber's text differed from the written Spanish sentences by 10.43 errors per 100 tokens, against 4.30 for the words alone.
- In our October 2026 benchmark, counting punctuation and capital letters as a reader sees them, Apple SpeechTranscriber's text differed from the written French sentences by 10.34 errors per 100 tokens, against 6.59 for the words alone.
- In our October 2026 benchmark, counting punctuation and capital letters as a reader sees them, Apple SpeechTranscriber's text differed from the written Italian sentences by 10.68 errors per 100 tokens, against 4.15 for the words alone.
- In our October 2026 benchmark, counting punctuation and capital letters as a reader sees them, Apple SpeechTranscriber's text differed from the written Portuguese sentences by 100.00 errors per 100 tokens, against 100.00 for the words alone.