Serhiy Stetskovych
Serhiy Stetskovych
Confirm. We have the same issue on the latest chrome version.
I have the same issue, I run it in docker on ubuntu 20.04. I also use write_http plugin with minimal set of collection plugins: ``` LoadPlugin cpu LoadPlugin df LoadPlugin...
You have to downgrade torch, but I can't say to which version.
I don't think it is whisper model problem, I have file that works without any issues on other implementations. I can share it if you want. This is how transcript...
Yes, you are right, my input was stereo, thank you. Now it works, but output is much worse than original.
I use this checkpoint https://drive.google.com/drive/folders/1JK9VqgfQsWEPOFUkp9Y5OR62G9i3disf Source is 12kHz and output file generated in 16kHz. As I understand I run incorrect command: ``` python predict.py dset=4-16 experiment=aero_4-16_512_256 ``` but it should...
As I remember it was broken and you need to fix it manually. You can look in to notebook file to understand how to run inference and fix it according...
Thank you for your fast answer. We have found files that causes crash, but they looks normal, after removing that file we are able to run train but then it...
Oh you have edited you answer. It was a crash. If you need more info I can try to run it again and will tell you. But I think I...
No it doesn't crash during the training. I got crash after I loaded trained checkpoint on synthesis method.