yangmingwanli

Results 2 issues of yangmingwanli

Hi Timo, The demo run OK with provided audio sequence. But when using a self recorded audio file (native English, mono channel, same sample rate and bit rate .wav file),...

### Question followed the new guide https://github.com/haotian-liu/LLaVA/blob/main/docs/Finetune_Custom_Data.md used finetune_task_lora.sh without --group_by_modality_length dataset includes only a few hundreds of images. one round of user assistant conversation per image. user message is...