code-faster | Sublime Text plugin for programming contests | Code Editor library

The server code included in Kaldi is kinda a toy, you can not use it in real applications just because it doesn't support multiprocessing and doesn't allow multiprocessing with a shared model. It is a total waste of resources to use it.

If you need a Kaldi websocket server you can check VOSK server. It can run as many parallel requests as you need and allows you to control the load intelligently. It is also simple to configure vosk-server behind NGINX websocket proxy and distribute load across many nodes.

Without multiprocessing, I executed this code in 0.07s. The multiprocessing version took 0.28s. Create some pool of processes take some times and it may not be worth it.

I recommend not printing during the process as it could create a funnel effect (I/O is always an issue for concurrent processes)

Changing a little bit your code :

NOSPLIT:

Similarly, NASM will split [eax*2] into [eax+eax] because that allows the offset field to be absent and space to be saved; in fact, it will also split [eax*2+offset] into [eax+eax+offset].
You can combat this behaviour by the use of the NOSPLIT keyword: [nosplit eax*2] will force [eax*2+0] to be generated literally.
[nosplit eax*1] also has the same effect. In another way, a split EA form [0, eax*2] can be used, too. However, NOSPLIT in [nosplit eax+eax] will be ignored because user's intention here is considered as [eax+eax].