search

ina-foss / inaSpeechSegmenter

CNN-based audio segmentation toolkit. Allows to detect speech, music, noise and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.
MIT License
717 stars 127 forks source link

Getting "terminated: Application failed to start: not available" for longer audio files #67

Closed suraj143rosy closed 2 years ago

suraj143rosy commented 2 years ago

When i ran this for a 30 mins audio file , I am getting the below error. "terminated: Application failed to start: not available" .

Can you please check and update what this is related to?

DavidDoukhan commented 2 years ago

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

Expected Behavior

Current Behavior

Steps to Reproduce

1. 2. 3. 4.

Additional infos

suraj143rosy commented 2 years ago

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)

DavidDoukhan commented 2 years ago

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....

suraj143rosy commented 2 years ago

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

DavidDoukhan commented 2 years ago

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

suraj143rosy commented 2 years ago

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

DavidDoukhan commented 2 years ago

cool!