{
 "id": "neh7777/Pretraining-V1",
 "owner": "neh7777",
 "name": "Pretraining-V1",
 "downloads": 4803,
 "likes": 2,
 "last_modified": "2026-05-15T04:52:02.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-to-speech",
  "automatic-speech-recognition"
 ],
 "citation": "If you use this dataset, please cite the original source datasets as appropriate:\n\n- **IndicTTS**: SPRINGLab/IndicTTS\n- **Kathbath**: ai4bharat/Kathbath\n- **SYSPIN**: kenpath/tts-SYSPIN\n- **IndicVoices-R**: ai4bharat/indicvoices_r\n- **Rasa**: ai4bharat/Rasa\n- **Shrutilipi**: ai4bharat/Shrutilipi\n- **Microsoft Speech Corpus Indian**: deepdml/microsoft-speech-corpus-indian\n- **SpiCor**: kenpath/tts-SPICOR\n- **Common Voice 22 (SIDON)**: sarulab-speech/commonvoice22_sidon (derived from Mozilla Common Voice Corpus 22.0, CC-0)\n\n---",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "1c18d6ddb2b42965ec9caff638a6978bdce4953a",
 "stated_evidence": "https://huggingface.co/datasets/neh7777/Pretraining-V1/blob/1c18d6ddb2b42965ec9caff638a6978bdce4953a/README.md",
 "file_evidence": "https://huggingface.co/datasets/neh7777/Pretraining-V1/tree/1c18d6ddb2b42965ec9caff638a6978bdce4953a",
 "card_nc": false
}