Optimized version

[Elsaam2y]

Hi,

thanks for this amazing work. I have worked a bit on this project to remove deep speech dependancies beside some other optimization efforts. You can find this optimized version here:

https://github.com/Elsaam2y/DINet_optimized

This version would improve the inference latency by 50-60%. I can also open a PR here in this repo if you are willing to accept external PRs.

Thanks

[NumairSayed]

hey @Elsaam2y . I dont have access to GPUs and I cannot buy colab, can you let me know about the best inference speed you were able to achieve?? Thanks