Questions tagged [ctc]

CTC or “connectionist temporal classification” is a machine learning technique for mapping dense input data to shorter output sequences in the same order.

85 questions
2
votes
0 answers

CTC loss incorrect computation

Python's input: sequence1 = [0, 1] output1 = [[1, 0, 0],[0, 1, 0]] loss = tf.compat.v1.nn.ctc_loss( labels=tf.sparse.from_dense([sequence1]), …
kisak
  • 21
  • 3
2
votes
1 answer

Adding CTC Loss and CTC decode to a Keras model

I am trying to solve a use case of handwritten text recognition. I have used CNN and LSTM to create a network. The output of this needs to be fed to a CTC layer. I could find some codes to do this in native tensorflow. Is there an easier option for…
NinjaR
  • 621
  • 6
  • 22
2
votes
0 answers

Why word-level language model should help in beam search decoding in ASR?

I was experimenting with beam search decoding of an acoustic model trained with CTC loss trained on an automatic speech recognition task. The version I was using was based on this paper. However, even though many sources describe integration of…
2
votes
1 answer

Does NOT `tf.nn.ctc_beam_search_decoder()` support GPU in TensorFlow2?

Now, I try to use tf.nn.ctc_beam_search_decoder() on GPU. But I have a problem that it does not use GPU. I was able to check that other tensorflow functions(e.g. Reshape and SigmoidGrad etc.) run on GPU. But some ones including…
YK_
  • 23
  • 3
2
votes
1 answer

What do confidence scores mean in speech recognition?

A lot of speech to text services (such as Google's) provide a confidence score. At least for Google it is between 0 and 1, but is clearly not the probability that a particular transcription is correct, as confidences for alternative transcriptions…
2
votes
0 answers

Understanding K.ctc_decode

Here is Keras test test_ctc_decode_greedy for ctc_decode. Here is my slightly modified example: def test_ctc_decode_greedy(): def _remove_repeats(inds): is_not_repeat = np.insert(np.diff(inds).astype(np.bool), 0, True) return…
mrgloom
  • 20,061
  • 36
  • 171
  • 301
2
votes
1 answer

How do you use tensorflow ctc_batch_cost function with keras?

I have been trying to implement a CTC loss function in keras for several days now. Unfortunately, I have yet to find a simple way to do this that fits well with keras. I found tensorflow's tf.keras.backend.ctc_batch_cost function but there is not…
2
votes
0 answers

Custom CTC loss function in Keras/Tensorflow

I feel like I'm fundamentally misunderstanding something. I went through the Keras documentation to no avail. I'm trying to implement the ctc_batch_cost loss for my neural network. My neural network ends with an LSTM layer which returns sequences…
Felix
  • 428
  • 3
  • 9
2
votes
1 answer

Why do I keep getting an error saying "maximum recursion depth exceeded while calling a Python object" in Keras from Tensorflow 2.0?

I am trying to train a stacked neural network architecture with CNNs, GRUs and a CTC in tensorflow 2.0's edition of Keras. I keep getting an error saying "RecursionError: maximum recursion depth exceeded while calling a Python object". I have tried…
2
votes
1 answer

What's the difference between tf.nn.ctc_loss with pytorch.nn.CTCLoss

For the same input and label: the output of pytorch.nn.CTCLoss is 5.74, the output of tf.nn.ctc_loss is 129.69, but the output of math.log(tf ctc loss) is 4.86 So what's the difference between pytorch.nn.CTCLoss with tf.nn.ctc_loss? tf:…
2
votes
0 answers

Combining the outputs of multiple models with CTC output layer(ensemble)

I am trying to combine the results of different models to give a better result(like voting in classification). Output of my models are from ctc layer, which is probability distribution of the output class for time stamp. It has 2d output (T X P) T…
newlearnershiv
  • 350
  • 1
  • 9
1
vote
0 answers

ImportError: cannot import name 'keras_ctcmodel' from 'keras'

I'm trying to run a Connectionist Temporal Classification Model (Automatic Speech Recognition), and below is the beginning code I got from the example.py in https://github.com/cyprienruffino/CTCModel/blob/master/example.py: import os !pip install…
ihavenoidea
  • 41
  • 1
  • 3
1
vote
1 answer

TypeError: Expected keras.losses.Loss, found function

I want to build a TFF model for speech recognition systems. For this, I use the CNN-GRU model architecture with a CTC loss function. but I got error when I wanted to build_federated_averaging_process and think it's about the ctc_loss function but I…
1
vote
2 answers

how to save ocr model from keras author-A_K_Nain

Im studying tensorflow ocr model from keras example authored by A_K_Nain. This model use custom object (CTC Layer). It is in the site:https://keras.io/examples/vision/captcha_ocr/ I trained model using my dataset and then the result of prediction…
PlusCoding
  • 13
  • 3
1
vote
1 answer

how to implement word beam search ctc to keras?

I am building a handwriting recognition model which currently has 88% validation accuracy. I came across this github page which can help the model achieve more accurate predictions using a dictionary. The problem is I don't know how to implement…