Swahili
7/4/en-7/fr-6
Swahili (ISO 639-3 swa). In words: tens of millions of fluent speakers; tens of thousands of monolingual sentences; tens of millions of sentences parallel with English, millions of sentences parallel with French.
Score breakdown
| Component | Digit | Raw count | Reads as | Top corpus |
|---|---|---|---|---|
| Speakers (S) | 7 | 15,437,390 | tens of millions | — |
| Monolingual (M) | 4 | 10,964 | tens of thousands | — |
Bilingual · English (en) | 7 | 23,513,175 | tens of millions | NLLB |
Bilingual · French (fr) | 6 | 8,057,969 | millions | CCMatrix |
Benchmark performance
Published zero-shot results used to validate the notation (see the RAN Paper).
| Task | Benchmark | Metric | Score |
|---|---|---|---|
| MT | NLLB-200 FLORES | chrF++ | 60.7 |
| NER | XTREME WikiANN XLM-R Large | F1 | 70.5 |
Note
Macrolanguage (sw); Wikidata count is L1-only
Sources
- Wikidata: Q7838
- Counts use the sources this site applies consistently (see the overview) — Ethnologue (speakers), OSCAR 23.01 (monolingual), OPUS (bilingual) — except where this page's notes record a different source. The top corpus for each bilingual partner is shown in the breakdown above.
See the RAN overview for how scores are computed and what they mean.