FLEURS
Few-shot Learning Evaluation of Universal Representations of Speech - a parallel speech dataset in 102 languages built on FLoRes-101 with approximately 12 hours of speech supervision per language for tasks including ASR, speech language identification, translation and retrieval
Progress Over Time
Interactive timeline showing model performance evolution on FLEURS
State-of-the-art frontier
Open
Proprietary
FLEURS Leaderboard
5 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Google | 8B | 1.0M | $0.07 / $0.30 | ||
| 2 | Google | — | 1.0M | $0.15 / $0.60 | ||
| 3 | Google | — | 2.1M | $2.50 / $10.00 | ||
| 4 | Google | — | 33K | $0.50 / $1.50 | ||
| 5 |  Alibaba Cloud / Qwen Team | 7B | — | — |
Notice missing or incorrect data?
FAQ
Common questions about FLEURS
Few-shot Learning Evaluation of Universal Representations of Speech - a parallel speech dataset in 102 languages built on FLoRes-101 with approximately 12 hours of speech supervision per language for tasks including ASR, speech language identification, translation and retrieval
The FLEURS paper is available at https://arxiv.org/abs/2205.12446. This paper provides detailed information about the benchmark methodology, dataset creation, and evaluation criteria.
The FLEURS leaderboard ranks 5 AI models based on their performance on this benchmark. Currently, Gemini 1.5 Flash 8B by Google leads with a score of 0.864. The average score across all models is 0.226.
The highest FLEURS score is 0.864, achieved by Gemini 1.5 Flash 8B from Google.
5 models have been evaluated on the FLEURS benchmark, with 0 verified results and 4 self-reported results.
FLEURS is categorized under language and speech to text. The benchmark evaluates audio models with multilingual support.