Automatic_Speech_Recognition
Automatic_Speech_Recognition copied to clipboard
zzw922cn
End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow
I tried to use your code "Automatic_Speech_Recognition" and confronted with a problem while setting it. When I ran the code with the command "Python3 main/timit_train.py", a FileNotfoundError occurred, which argued...
LibriSpeech dataset (e.g. train-clean-100) is split into multiple directories during preprocessing. Then during training, the code iterates through these directories: https://github.com/zzw922cn/Automatic_Speech_Recognition/blob/master/speechvalley/main/libri_train.py#L159 The problem is that for each directory, a new...
hi, i have been trying to train words like command, backspace, one two, etc . the preprocessing n training went well. But the result of testing produces a long sequence...
今天偶然发现，在您的程序中完成特征提取之后的npy文件里面的数据不是39*1，而是39*n（根据不同的语音n取值不一样，有292,370等），我之前一直以为您的预处理程序处理完语料产生的就是一个长度为39的特征向量，之前接触的其他的语音识别特征提取都是一个39维的特征向量，为什么您特征提取完的矩阵这么大？后面是否有将他转化为长度为39的特征向量的操作？我并没有在您的程序中找到，望能指教，非常感谢
Hi I have been trying to get your solution working on Windows 10. It seems very very promising. However i am having several difficulties trying to understand the exact nature...
when i make file for Making all in M4 make[1]: Entering directory '/home/techv/Desktop/test/libsndfile-1.0.28/M4' make[1]: Nothing to be done for 'all'. make[1]: Leaving directory '/home/techv/Desktop/test/libsndfile-1.0.28/M4' Making all in Win32 make[1]: Entering...
Hey, thanks for the great work but I see some inconsistency with the code. I am trying to run libri_preprocess.py but I see some print (print f, that is not...
HI when I run timit_train.py, error as follow , how can I slove it? 2018-06-08 17:26:00.908082: I tensorflow/core/common_runtime/bfc_allocator.cc:680] Stats: Limit: 10625279591 InUse: 7350513920 MaxInUse: 7464792320 NumAllocs: 82 MaxAllocSize: 3656908800 2018-06-08...
Dear, How to start the project?Any advice? 大佬你好！ 请教下如何开始您的工作，有没有步骤和建议？ 多谢！
您好 我看了一下您的 list_to_sparse_tensor函数（utils内），我不太清楚mapping和group的作用是什么，因为好像在解码的时候，是直接将输出的SparseTensor送进了output_to_sequence，而这个函数貌似没有使用到group和mapping？ 非常感谢！
