-
Implement a bi-directional LSTM or GRU-based transcription model with a CTC loss function.
-
Hi,
I have been trying to get this great project up and running. I was able to run C simulation and C Synthesis successfully under Vivado HLS. After that, I tired to run C/RTL co-simulation hoping …
-
In the example of Chapter 6 asr-lstm-ctc, it only has one wav file and one txt file to train. Now I would like to use Tedlium dataset to train, how can I rewrite the program? If I set the batch size a…
-
Hi,
I would like to build a CRNN (CNN-LSTM-CTC) for handwritten recognition, the output of LSTM is sequences of size 512 x 32 (with 512 time-steps) and the CTC label sequence has the size of 80 (char…
-
hello,请问为什么我使用您的程序ctc loss从一开始就为nan呢？希望您指导一下，非常感谢~
下面是显示的内容：
Using gpu device 0: GeForce GTX 980 Ti (CNMeM is disabled, cuDNN not available)
C:\Anaconda\lib\site-packages\theano\tensor\signal\downs…
-
I'm training a CRNN to do captcha recognition. Without CTC, it reach 90% sequence for certain type of captcha. The problem is it can only recognize captchas with similar character segmentation. So I t…
-
Hi,
it stops after this message:
[NOTE] TOKEN_ACCURACY refers to token accuracy, i.e., (1.0 - token_error_rate).
EPOCH 1 RUNNING ... TAG: 10_1.0 lrate 4e-05,
Brief error:
ERROR (train-ctc-paral…
-
when I exec import, report error:
```
# In SeanNaren/warp-ctc/pytorch_binding
>>> from warpctc_pytorch import CTCLoss
Traceback (most recent call last):
File "", line 1, in
File "/data/110…
-
[inference.zip](https://github.com/PaddlePaddle/Paddle2ONNX/files/7258385/inference.zip)
There's 3 ops are not supported yet
=========== fc ===========
=========== ctc_align ===========
==========…
-
hello , I tried to run you code about LSTM-CTC, but warpctc doesnt work well .I wonder if you met this problem when run the mxnet with warpctc,I'm looking forward for you help.Here is what I did:
1. …