利用paddlespeech预训练模型进行声音分类模型调优

[XiaoqingWang]

利用paddlespeech预训练模型进行声音分类模型调优 https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/tutorial/cls/cls_tutorial.ipynb 1、发现同样的测试样本，特征提取也一样，但多次预测，每次预测的结果对应的分类类型都不一样 a、有尝试过固定随机种子，问题没解决 b、尝试导出静态模型进行推理，但predict时提示找不出lod_audio包（脚本参考https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/examples/esc50/cls0/local/infer.sh） 问题情况：paddleaudio 1.01 load_audio包找不到，帮忙确认一下哪个版本有，谢谢 from paddleaudio.backends import soundfile_load as load_audio报错 ImportError Traceback (most recent call last) Cell In[12], line 21 19 import yaml 20 from paddle.audio.features import LogMelSpectrogram ---> 21 from paddleaudio.backends import soundfile_load as load_audio 22 #import paddle.audio.load as load_audio 24 from paddleaudio.utils import logger

ImportError: cannot import name 'soundfile_load' from 'paddleaudio.backends' (C:\Users\JM.conda\envs\pg\lib\site-packages\paddleaudio\backends_init_.py)