{
 "id": "AfriSpeech/afrispeeches",
 "owner": "AfriSpeech",
 "name": "afrispeeches",
 "downloads": 533,
 "likes": 0,
 "last_modified": "2026-10-05T17:44:11.000Z",
 "stated_licence": "cc-by-nc-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "automatic-speech-recognition"
 ],
 "citation": "Every audio segment in **AfriSpeeches** is attributed to the specific statesman who delivered it:\n\n- **Full Attribution:** Every record includes the leader's full name, country of state, national ISO code, spoken language, speech title, and the verifiable source recording URL.\n- **Natural Oratorical Chunking:** Rather than slicing audio at arbitrary time boundaries, speeches are split strictly at natural pauses identified via Silero Voice Activity Detection (median segment duration of **6.5 minutes**, capped at <= 8.0 minutes). This preserves complete oratorical thoughts, rhetorical delivery, and natural cadence.\n- **Verbatim Transcriptions:** Paired with complete speech-to-text transcriptions verified for acoustic continuity and textual integrity.\n- **Embedded Audio:** Audio is encoded in **24 kHz mono FLAC** embedded directly inside browser-streamable Parquet shards, eliminating the need for complex extraction or separate multi-gigabyte archive downloads.\n\n---\n\n\nThis dataset is released under the **Creative Commons Attribution-NonCommercial 4.0 International (CC-BY-NC 4.0)** license.\n\n- **Attribution:** When using this dataset in academic research or applications, please cite the **[AfriSpeech](https://huggingface.co/AfriSpeech)** / **[Ghana NLP](https://ghananlp.org)** community and cite the attributed speakers.\n- **Non-Commercial:** Intended for non-commercial academic and linguistic research.",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-4.0) is classified as having use restrictions.",
 "revision": "bfb91e7528940f673de0edd9c3b7fb62354e61e0",
 "stated_evidence": "https://huggingface.co/datasets/AfriSpeech/afrispeeches/blob/bfb91e7528940f673de0edd9c3b7fb62354e61e0/README.md",
 "file_evidence": "https://huggingface.co/datasets/AfriSpeech/afrispeeches/tree/bfb91e7528940f673de0edd9c3b7fb62354e61e0",
 "card_nc": false
}