Skip to content
This repository has been archived by the owner on Feb 22, 2022. It is now read-only.

Latest commit

 

History

History
30 lines (25 loc) · 1.12 KB

ROADMAP.md

File metadata and controls

30 lines (25 loc) · 1.12 KB
Raw

Roadmap

Last Update: 2021-03-13

List of things achieved:

  1. Create a simple architecture to handle multiple aimodels. ✔️
  2. Run a simple inference from one model. ✔️
  3. Record, process and play one single audio. ✔️
  4. Do step 3 in loops. ✔️
  5. Support for tensorflow serving. ✔️
  6. Thread/Process and colorful output. ✔️
  7. Achieve real-time processing and multi-process. (Tensorflow only). ✔️

List of things to do, not sorted and looking for help:

  1. Increase the quality by increasing the sample rate of output. (Also requires re-training and new weights).
  2. Auto re-configuration after fails creating new mic or speakers.
  3. Create a mirror from output audio to a virtual microphone.
  4. CI/CD for Windows, MacOs & Linux.
  5. Buildpacks for Windows, MacOs & Linux.
  6. Release docker images.
  7. GUI to select input, output and aimodels to process.
  8. Build a web app to host releases.
  9. Support for mobile devices if possible.
  10. Support for cloud processing.
  11. Support for stereo channeling instead of just mono.

Please, let me know if you want to be a contributor, open pull-requests or ask me via PM.