hi @SWivid i just make a lot update in gradio
in create you can select Tokenizer pinyin or char
easy create project and then select form combox
![image](https://github.com/user-attachments/a...
@SWivid This one I will not merge myself because I need your confirmation. This adds an AI Voice Chat feature using LLM Qwen2.5-3B (very fast), 3gb only, but needs pip install transformers_stream_g...
I noticed the function convert_char_to_pinyin wasn't correctly tokenizing my text according to my vocab. This only affects custom vocabs, but the function was returning every word as a token, even ...
> Hi @lpscr , maybe you could help check if compatible with current version, or a re-run of dataset preparation process needed. Will merge if no big conflicts, together with the repo reorganization...
> @lpscr just temporarily lol. you can see from `dev` branch now, will go for that structure, though import and path dependencies not solved yet, will do that tomorrow when i wake up. after that fi...