Search results
Jump to navigation
Jump to search
Create the page "Datasets" on this wiki! See also the search results found.
- ...216k hours of speech, making it one of the largest openly-available speech datasets. Emilia-Large combines the original 101k-hour Emilia dataset (licensed unde from datasets import load_dataset ...4 KB (554 words) - 03:43, 19 September 2025
- * Pre-encoded datasets available (Emilia-YODAS compressed from 1.7 TB to 41 GB) ...1 KB (176 words) - 02:33, 23 December 2025
- Based on evaluation across multiple datasets (LibriSpeech-test-clean, SeedTTS test-zh/en, AIShell-1), IndexTTS2 demonstr ...8 KB (986 words) - 20:46, 21 September 2025