speech_recognition
speech_recognition copied to clipboard
tensorflow.python.framework.errors_impl.NotFoundError:
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
编码问题?是在不行还是自己训练一个吧!
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
[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
wav_files, text_labels = utils.get_wavs_lables() 这行代码你debug进去看看,返回的是什么?
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
我用你上传的test语音训练可以运行,但是总是重复那几句
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
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
@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。
测试结果:
@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