search

nl8590687 / ASRT_SpeechRecognition

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
https://asrt.ailemon.net
GNU General Public License v3.0
7.85k stars 1.9k forks source link

无法正确运行asrserver.py，报Data loss #243

Closed bitsf closed 3 years ago

bitsf commented 3 years ago

Hi, 我下载0.6.1 release 后，并且在我的Mac 上安装了最新的 tensorflow(2.5.0), keras(2.4.3), h5py(3.1.0) 等，在执行 python asrserver.py 后会提示错误如下 2021-06-02 14:54:15.312718: W tensorflow/core/util/tensor_slice_reader.cc:95] Could not open model_speech/speech_model251_e_0_step_625000.model: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator? image

nl8590687 commented 3 years ago

请看ASRT项目文档上写的内容，已经发布的v0.6.1版要用tf 1.15版本，keras 2.3.1 最新master的才可以用tf 2.x