tomasz-oponowicz / spoken_language_identification Goto Github PK
View Code? Open in Web Editor NEWIdentify a spoken language using artificial intelligence (LID).
License: MIT License
Identify a spoken language using artificial intelligence (LID).
License: MIT License
Hi running model.py. I am getting following error
Traceback (most recent call last):
File "model.py", line 209, in
batch_size=8)
File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 1002, in fit
validation_steps=validation_steps)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1630, in fit
batch_size=batch_size)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1480, in _standardize_user_data
exception_prefix='target')
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 123, in _standardize_input_data
str(data_shape))
ValueError: Error when checking target: expected activation_6 to have shape (2,) but got array with shape (1,)
Can you please help me with this. Complete output is
Using TensorFlow backend.
('Classes:', ['en', 'hi'])
[1, 2]
1
[1, 2]
[train] labels: (6960, 1), features: (6960, 40, 996, 1)
[1]
[train] labels: (3480, 1), features: (3480, 40, 996, 1)
conv2d_1 (Conv2D) (None, 40, 996, 16) 160
activation_1 (Activation) (None, 40, 996, 16) 0
max_pooling2d_1 (MaxPooling2 (None, 20, 498, 16) 0
conv2d_2 (Conv2D) (None, 20, 498, 32) 4640
activation_2 (Activation) (None, 20, 498, 32) 0
max_pooling2d_2 (MaxPooling2 (None, 10, 249, 32) 0
conv2d_3 (Conv2D) (None, 10, 249, 64) 18496
activation_3 (Activation) (None, 10, 249, 64) 0
max_pooling2d_3 (MaxPooling2 (None, 5, 125, 64) 0
conv2d_4 (Conv2D) (None, 5, 125, 128) 123008
activation_4 (Activation) (None, 5, 125, 128) 0
max_pooling2d_4 (MaxPooling2 (None, 5, 25, 128) 0
conv2d_5 (Conv2D) (None, 5, 25, 256) 491776
activation_5 (Activation) (None, 5, 25, 256) 0
max_pooling2d_5 (MaxPooling2 (None, 5, 5, 256) 0
average_pooling2d_1 (Average (None, 1, 1, 256) 0
flatten_1 (Flatten) (None, 256) 0
dense_1 (Dense) (None, 32) 8224
dropout_1 (Dropout) (None, 32) 0
dense_2 (Dense) (None, 2) 66
Total params: 646,370
Trainable params: 646,370
Non-trainable params: 0
Traceback (most recent call last):
File "model.py", line 209, in
batch_size=8)
File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 1002, in fit
validation_steps=validation_steps)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1630, in fit
batch_size=batch_size)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1480, in _standardize_user_data
exception_prefix='target')
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 123, in _standardize_input_data
str(data_shape))
ValueError: Error when checking target: expected activation_6 to have shape (2,) but got array with shape (1,)
Hi, accuracy does not improve when trainning the model(15G data). acc is just 0.34. Do you know why? Thank you.
Hi ,
Thanks a lot for your work ,
Can you please explain why you removed cepstral coefficients calculation?
Hi, I also working on LID, my online environment is not clean, there are bg musics or noize in online audio, how can I process this problem?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.