Divyesh Rajpura

Ok. I will look into that. Thank You...

Hi, I am getting the similar issue. I have trained zipformer with --use-transducer false and --use-ctc true. During decoding, it stuck at the stage of get_lattice in zipformer/ctc_decoding.py Below are...

Please find the attached screenshot for your reference 

I had put down the logging at various stages to figure the step which is causing an issue.

> Are you able to get the stack trace after it gets stuck in get_lattice by manually pressing ctrl + c? No, Actually it does not even stop with `ctrl...

@csukuangfj , I have changed the device from GPU to CPU. With this change, the decoding terminated automatically and below is the stack trace ``` [F] /var/www/k2/csrc/array.h:176:k2::Array1 k2::Array1::Arange(int32_t, int32_t) const...

@csukuangfj, @JinZr Just wanted to check if you had a chance to go through the above issue.

@csukuangfj , Thanks for the response The version details for the k2 is `1.24.4.dev20240223+cuda12.1.torch2.2.1`

I have already tried to reduce till 100s, let me reduce further.

The audio duration in test data are in a range of 2 to 15s. Reducing max duration helped. The max value for `--max-duration` worked for me is 15. If increase...