search

bytedance / SALMONN

SALMONN: Speech Audio Language Music Open Neural Network
https://bytedance.github.io/SALMONN/
Apache License 2.0
1.01k stars 78 forks source link

使用 7B 模型，有的时候无法生成 audio caption #37

Open yt605155624 opened 6 months ago

yt605155624 commented 6 months ago

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