I want to learn to use your model, but due to my current computer performance limitations, I am not able to train a model, so ask me if you can send me your trained model.

[Dylan-Dyb]

Thanks

[liangstein]

https://www.dropbox.com/s/anvw5x7bmjsm94u/listen_model.chk?dl=0

[Alvin2580du]

Thank you

[zhaowz]

use your code and load your model but have error, can you help me?
Traceback (most recent call last):
File "/home/zhaozhe/tensorflow-gpu_zz131/deeplearning/speech_proj/Chinese-speech-to-text/speech_to_text.py", line 61, in
model.load_weights(DIR+"/listen_model.chk");
File "/home/zhaozhe/python27/local/lib/python2.7/site-packages/keras/engine/topology.py", line 2652, in load_weights
f, self.layers, reshape=reshape)
File "/home/zhaozhe/python27/local/lib/python2.7/site-packages/keras/engine/topology.py", line 3176, in load_weights_from_hdf5_group
reshape=reshape)
File "/home/zhaozhe/python27/local/lib/python2.7/site-packages/keras/engine/topology.py", line 3070, in preprocess_weights_for_loading
weights[0] = np.transpose(weights[0], (3, 2, 0, 1))
File "/home/zhaozhe/python27/local/lib/python2.7/site-packages/numpy/core/fromnumeric.py", line 575, in transpose
return _wrapfunc(a, 'transpose', axes)
File "/home/zhaozhe/python27/local/lib/python2.7/site-packages/numpy/core/fromnumeric.py", line 62, in _wrapfunc
return _wrapit(obj, method, *args, **kwds)
File "/home/zhaozhe/python27/local/lib/python2.7/site-packages/numpy/core/fromnumeric.py", line 42, in _wrapit
result = getattr(asarray(obj), method)(*args, **kwds)
ValueError: axes don't match array

[liangstein]

are you using the same version of python and keras? 2018-03-02 17:02 GMT+08:00 zhaowz <[email protected]>:

…

use your code and load your model but have error, can you help me? Traceback (most recent call last): File "/home/zhaozhe/tensorflow-gpu_zz131/deeplearning/speech_ proj/Chinese-speech-to-text/speech_to_text.py", line 61, in model.load_weights(DIR+"/listen_model.chk"); File "/home/zhaozhe/python27/local/lib/python2.7/site-packages/keras/engine/topology.py", line 2652, in load_weights f, self.layers, reshape=reshape) File "/home/zhaozhe/python27/local/lib/python2.7/site-packages/keras/engine/topology.py", line 3176, in load_weights_from_hdf5_group reshape=reshape) File "/home/zhaozhe/python27/local/lib/python2.7/site-packages/keras/engine/topology.py", line 3070, in preprocess_weights_for_loading weights[0] = np.transpose(weights[0], (3, 2, 0, 1)) File "/home/zhaozhe/python27/local/lib/python2.7/site-packages/numpy/core/fromnumeric.py", line 575, in transpose return _wrapfunc(a, 'transpose', axes) File "/home/zhaozhe/python27/local/lib/python2.7/site-packages/numpy/core/fromnumeric.py", line 62, in _wrapfunc return _wrapit(obj, method, *args, **kwds) File "/home/zhaozhe/python27/local/lib/python2.7/site-packages/numpy/core/fromnumeric.py", line 42, in _wrapit result = getattr(asarray(obj), method)(*args, **kwds) ValueError: axes don't match array — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#2 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AX1PHEjfZtLT0AhYies1Pj35Tu1aVwWoks5taQqUgaJpZM4QpYke> .

[nathphoenix]

Hi @liangstein @Alvin2580du please can you help me with the pretrained model, tried to download from google drive but not responding, wanted to test the output before training,
i have the error below stating the pretrain model is not available

[liangstein]

https://www.dropbox.com/s/ujiardfgl2z51ya/listen_model.chk?dl=0

[nathphoenix]

Thank you so much, I was able to get the output which is the same with yours @liangstein ,
please one last thing, can you please help me with the format of the dataset so it can help me in creating my own dataset.
A screenshot of your dataset will be very helpful.
And please i want to use the LJSpeech dataset with it, i just want to understand how you structure your dataset.
Thanks in advance

[liangstein]

This was done too long ago, I forget the details. If you can find the Chinese audio dataset I used in this repositary, it will not be hard to find out the dataset format.