Paza Bench
A speech recognition benchmark for African languages released under Microsoft's Paza project, covering 39 African languages and evaluating 53 advanced models to measure ASR performance on low-resource languages.
Timeline (last 90 days)
In the Paza Bench benchmark, the multi-task LLM had the best accuracy, the encoder-only model followed closely, and the encoder-decoder model had the weakest accuracy; but in inference speed, the encoder-only model performed best, the encoder-decoder came second, and the LLM-based model lagged clearly behind.
In the performance comparison of the six Kenyan languages, Swahili and Kikuyu of the Bantu family consistently performed best, while Maasai and Kalenjin of the Nilotic family performed worst; the Paza Bench benchmark across 39 languages reached a consistent conclusion: Nilotic and Afroasiatic languages consistently lag behind, and the conclusion still holds after the second version expanded to 61 languages.
All Facts (2)
In the Paza Bench benchmark, the multi-task LLM had the best accuracy, the encoder-only model followed closely, and the encoder-decoder model had the weakest accuracy; but in inference speed, the encoder-only model performed best, the encoder-decoder came second, and the LLM-based model lagged clearly behind.
50%UnverifiedIn the performance comparison of the six Kenyan languages, Swahili and Kikuyu of the Bantu family consistently performed best, while Maasai and Kalenjin of the Nilotic family performed worst; the Paza Bench benchmark across 39 languages reached a consistent conclusion: Nilotic and Afroasiatic languages consistently lag behind, and the conclusion still holds after the second version expanded to 61 languages.
50%