Getting "terminated: Application failed to start: not available" for longer audio files about inaspeechsegmenter HOT 7 CLOSED

Dear @suraj143rosy ,
Could you provide us more details on your issue, using the issue template bellow ?
I would suggest to pay a particular attention to the amount of RAM available in your host, and to the results of the unit tests.
Kind regards,

Please fill out this template for a bug report.

Make sure you ran the unit tests before submitting an issue and tell us if and where they fail.

System information

• OS Platform and Distribution (e.g., Linux Ubuntu 16.04):
• TensorFlow version:
• Python version:
• Running on GPU or CPU:
• output of command nvidia-smi (if GPU is used)
• CUDA/cuDNN version (if GPU is used):
• Using Docker:

Expected Behavior

Current Behavior

Steps to Reproduce

Additional infos

from inaspeechsegmenter.

System information
OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Google Cloud run
TensorFlow version: 2.7
Python version: 3.6.9
Running on CPU

Expected behavior:
It should work for larger audio files of duration more than 30 mins.
Current Behavior:
It is working for smaller files, but not for larger files. It is breaking at this line of the code only for larger audio files.
mag = numpy.fft.rfft(ahan, n_fft, axis=-1)

from inaspeechsegmenter.

Hi,

In order to help you, I would need to know the amount of RAM available on your host. I would also suggest you to monitor the RAM usage of the program when you launch it on large files.

inaSpeechSegmenter has beeen often used on recordings of several hours. It may crash if a very limited amout of RAM is available....

from inaspeechsegmenter.

The ram available on Cloud run is around 8 gb. Also the ram usage reaches max till 80%. Should i try on higher RAM?

from inaspeechsegmenter.

This would be my first advice ! I usually run it using 32 Gb RAM machines.

from inaspeechsegmenter.

Okay. Thank you. It worked on 16 gb RAM devices.

from inaspeechsegmenter.

cool!

from inaspeechsegmenter.