<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech

dc.contributor.authorAlexandre Conneau
dc.contributor.authoret al.
dc.date.accessioned2026-11-18T06:57:59Z
dc.date.issued2023
dc.descriptionHF metadata license: cc-by-4.0; redistribution permitted with attribution. Rights classification: FULL_TEXT_OK. Licence verified from: https://huggingface.co/api/datasets/google/fleurs (checked 2026-11-18). Source: Meta AI (FAIR) African relevance: Includes multiple African languages; key ASR evaluation benchmark. HF metadata license: cc-by-4.0; redistribution permitted with attribution.
dc.description.abstractSpeech version of FLoRes with ~2,009 n-way parallel sentences per language read by native speakers, for ASR, ST and language ID evaluation.
dc.identifier.doi10.48550/arXiv.2205.12446
dc.identifier.urihttps://huggingface.co/datasets/google/fleurs
dc.identifier.urihttps://library.dare.co.zw/handle/123456789/4991
dc.language.iso102 languages incl. Swahili, Amharic, Hausa, Yoruba, Igbo, Zulu
dc.publisherSLT / Hugging Face
dc.rightsCC-BY-4.0. Licence evidence: https://huggingface.co/api/datasets/google/fleurs. HF metadata license: cc-by-4.0; redistribution permitted with attribution.
dc.rights.holderDataset authors / Meta AI
dc.rights.licenseCC-BY-4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.sourceMeta AI (FAIR)
dc.source.urihttps://huggingface.co/datasets/google/fleurs
dc.subjectspeech recognition
dc.subjectspeech translation
dc.subjectevaluation
dc.subjectAfrican languages
dc.titleFLEURS: Few-shot Learning Evaluation of Universal Representations of Speech
dc.typedataset

Files