4 Commits

Author	SHA1	Message	Date
Dmitrii Mukhutdinov	87e217d065	[Whisper] Add large-v3 version support (#27336) ... * Enable large-v3 downloading and update language list * Fix type annotation * make fixup * Export Whisper feature extractor * Fix error after extractor loading * Do not use pre-computed mel filters * Save the full preprocessor properly * Update docs * Remove comment Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> * Add alignment heads consistent with each Whisper version * Remove alignment heads calculation * Save fast tokenizer format as well * Fix slow to fast conversion * Fix bos/eos/pad token IDs in the model config * Add decoder_start_token_id to config --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>	2023-11-20 17:36:48 +01:00
SeongWooChoi	42791a5753	🌐 [i18n-KO] Translated whisper.md to Korean (#26002) ... * docs: ko-whisper.md * fix: chatgpt draft * feat: manual edits * Feat: manual edits * fix: resolve suggestions Co-authored-by: Jungnerd <46880056+jungnerd@users.noreply.github.com> --------- Co-authored-by: Jungnerd <46880056+jungnerd@users.noreply.github.com>	2023-09-18 22:12:41 +02:00
MinJae Kang	be9438ed43	🌐 [i18n-KO] Translated llama2.md to Korean (#26047) ... * docs: ko-llama2.md * feat: chatGPT draft and manul edits * feat: added inline TOC * fix: inline TOC * fix: resolve suggestions Co-authored-by: Jungnerd <46880056+jungnerd@users.noreply.github.com> * fix: resolve suggestion Co-authored-by: Jungnerd <46880056+jungnerd@users.noreply.github.com> * fix: resolve suggestion Co-authored-by: Jungnerd <46880056+jungnerd@users.noreply.github.com> --------- Co-authored-by: Jungnerd <46880056+jungnerd@users.noreply.github.com>	2023-09-12 08:04:26 -07:00
Harheem Kim	d53606031f	🌐 [i18n-KO] Translated llama.md to Korean (#26044) ... * docs: ko-llama.md * fix: chatgpt draft * feat: manual edits * fix: resolve suggestions	2023-09-08 12:38:41 -07:00