Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hi all !
I am planning to merge CTC with KALDI for building end-to-end speech recognition system.
First of all, thanks for providing CTC as open source. I attribute yours in my future source code.
I first visited mohammadpz's page to download and test the code with toy-example.
But there is error related to type casting as Søren had before :
TypeError: expected type_num 7 (NPY_INT64) got 12
Apply node that caused the error: Elemwise{Add}[(0, 1)](Viterbi, shared_Viterbi)
Inputs types: [TensorType(int64, vector), TensorType(int64, vector)]
Inputs shapes: [(0,), (10,)]
Inputs strides: [(8,), (8,)]
Inputs values: [array([], dtype=float64), 'not shown']
It seems that there are type casting error as well as zero vector error .)
Unfortunately, THEANO_FLAGS='floatX=float64' does not change any result.
So I came here(@pbrakels) to test code, where it seems to be more recent code.
I have two question regarding this.
Q1) Any other solution for solving above error?
Q2) Is there any other code to test @pbrakel 's?
Thank you
Best regards,
Ken Kim