Just made a TTS tool based on Kitten TTS, fully browser based, no Python server backend: https://quickeditvideo.com/tts/
A tts model of this size should be industry standard!
I removed performance piece mostly because it's meaningless discussing performance without in the context of designated implementation and benchmarks.
Above catch is my point so I tweaked the words to `Performance is not good generally when dataset is huge unless you use a library support streaming parsing or writing.`
Thanks for your feedback. I am keeping on fixing documentations...
And yes, Blackgate is a reverse proxy for microservices. The reason not using Kong is because if you want to start a Kong cluster, you have to run a bunch of dependencies in several nodes, like Nginx, PostgreSQL, etc.
Blackgate is much simpler in this case. Write config, and Run instance. Nothing more.
I believe the architecture is not built in one-day. In early state, we can choose a simpler tool to avoid over-engineering.
I was wondering what you guys deploy python project dependencies. I made a small tool to package project&wheels and create virtualenv at server. Does anyone have better ways to do it?