bytedance/SALMONN

使用 7B 模型，有的时候无法生成 audio caption

Opened this issue · 0 comments

yt605155624 commented

image

prompt = 'Please describe the audio.'
    prompt = [
        cfg.config.model.prompt_template.format("<Speech><SpeechHere></Speech> " + prompt.strip())
    ]

如果是
prompt = 'Please write down what your hear in the audio.'
则全都无法生成
image