tensorflow.python.framework.errors_impl.NotFoundError:

[provenpeng]

tensorflow.python.framework.errors_impl.NotFoundError: FindFirstFile failed for: /home/kevin/workspaces/python/speech-new-test : ϵͳ\udcd5Ҳ\udcbb\udcb5\udcbdָ\udcb6\udca8\udcb5\udcc4·\udcbe\udcb6\udca1\udca3 ; No such process

用你的模型测试会有这种错误，求问怎么解决

[xxbb1234021]

编码问题？是在不行还是自己训练一个吧！

[provenpeng]

可是训练会有这种问题 C:\Users\zxchong\AppData\Local\Programs\Python\Python36\lib\site-packages\h5py_init_.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type. from ._conv import register_converters as _register_converters Traceback (most recent call last): File "c:\Users\zxchong\Desktop\zp\speech_recognition-master\train.py", line 13, in wav_files, text_labels = utils.get_wavs_lables() File "c:\Users\zxchong\Desktop\zp\speech_recognition-master\utils.py", line 17, in get_wavs_lables print(wav_files[0], text_labels[0]) IndexError: list index out of range

[FILE_DATA] wav_path=F:\xunlei\data\data_thchs30\train label_file=C:\Users\zxchong\Desktop\zp\speech_recognition-master\train_data\voice/test.word.txt savedir=C:\Users\zxchong\Desktop\zp\speech_recognition-master\train_data\voice\model savefile=speech.cpkt tensorboardfile=C:\Users\zxchong\Desktop\zp\speech_recognition-master\train_data\voice 不知道为什么

[xxbb1234021]

wav_files, text_labels = utils.get_wavs_lables() 这行代码你debug进去看看，返回的是什么？

[provenpeng]

可能是label_file没弄对，训练时 label_file用哪个？（我训练用的语音是data_thchs30\train），但是您发的data_thchs30的网站好像没有对应的label_file

[provenpeng]

我用你上传的test语音训练可以运行，但是总是重复那几句

[xxbb1234021]

就是在下载训练数据网页的最下面有个百度网盘 https://pan.baidu.com/s/1hqKwE00#list/path=%2F

[sunshinepython]

我下载了清华的那个数据，训练语音用wav_path =/data_thchs30/train， 但是label_file该怎么设置呢，清华的这个train文件中是有后缀为.wav.trn的文件，请问大佬训练的时候是怎么使用清华的这个数据的 @xxbb1234021

[chenyuqing]

@provenpeng @xxbb1234021 遇到同样的问题，已解决，修改checkpoint文件里面的路径为自己的路径，而不是kevin本身的路径。 kevin的路径是： model_checkpoint_path: "/home/kevin/workspaces/python/speech-new-test/speech.cpkt-101" all_model_checkpoint_paths: "/home/kevin/workspaces/python/speech-new-test/speech.cpkt-101"

修改为自己的路径：(我的是) model_checkpoint_path: "/home/tim/workspaces/speech_recognition-master/opt/tf/speechtest/speech.cpkt-101" all_model_checkpoint_paths: "/home/tim/workspaces/speech_recognition-master/opt/tf/speechtest/speech.cpkt-101"

然后就可以加载模型跑了。

[chenyuqing]

测试结果：

[Titook]

@provenpeng @xxbb1234021 遇到同样的问题，已解决，修改checkpoint文件里面的路径为自己的路径，而不是kevin本身的路径。 kevin的路径是： model_checkpoint_path: "/home/kevin/workspaces/python/speech-new-test/speech.cpkt-101" all_model_checkpoint_paths: "/home/kevin/workspaces/python/speech-new-test/speech.cpkt-101"

修改为自己的路径：(我的是) model_checkpoint_path: "/home/tim/workspaces/speech_recognition-master/opt/tf/speechtest/speech.cpkt-101" all_model_checkpoint_paths: "/home/tim/workspaces/speech_recognition-master/opt/tf/speechtest/speech.cpkt-101"

然后就可以加载模型跑了。

你好，我想问一下checkpoint文件里面怎么知道自己的路径呢