Open Ozawakun97 opened 1 month ago
据我实验,创建自有spk2info.pt,比微调效率高。
据我实验,创建自有spk2info.pt,比微调效率高。
创建自有的spk2info.pt 然后直接inference吗
据我实验,创建自有spk2info.pt,比微调效率高。
创建自有的spk2info.pt 然后直接inference吗
对,也可以使用自有spk2info进行instruct_inference
据我实验,创建自有spk2info.pt,比微调效率高。
会不稳定,韵律也经常出错,指望zero shot出能上线用的活、不经过一定数据的微调,无异于痴人说梦
据我实验,创建自有spk2info.pt,比微调效率高。
会不稳定,韵律也经常出错,指望zero shot出能上线用的活、不经过一定数据的微调,无异于痴人说梦
是,但这是比较简单的方法,修改一下文字中奇奇怪怪的标点符号,会好很多。
据我实验,创建自有spk2info.pt,比微调效率高。
怎么创建自有的spk2info.pt啊?
Hello dear Tongyi SpeechTeam I am interested with the controllable generation via instruction, and I want to fine-tune the model with my own version of data. Based on this, my question is, are there examples of the data for fine-tuning? Any requirements of the formatting? Besides, can the train.py script directly employed with fine-tuning? Are there any modifications to the script? Looking forward to your reply