speech-denoiser VS noise-repellent

This one: https://github.com/lucianodato/speech-denoiser

Frankly, what I hear is very similar to the results of classic spectral denoising, even with the characteristic artifacts (for Linux, there's Noise Repellent [1] available for advanced spectral denoising; there's also a ton of commercial spectral processors).

The demonstration could use more random background noises to separate it from spectral processors, and more varied vocabulary to separate it from RNNVoice [2] which tends to suppress breath and parts of sibilants, making the sound unnatural. The latency is also important - is it as low as in RNNVoice? What about the CPU load?

[1] https://github.com/lucianodato/noise-repellent

[2] https://github.com/werman/noise-suppression-for-voice

There's noise cancelling plugins. Example https://github.com/lucianodato/noise-repellent/releases/tag/v0.2.3 Or https://bertomaudio.com/denoiser-classic.html

Downloaded noise-repellent 0.2.3 for Linux at https://github.com/lucianodato/noise-repellent/releases

Plugins: LSP Plugins DISTRHO Plugins Calf Plugins TAP Plugins Noise-Repellent (The best thinge ever!)

The only thing it is missing natively which Audacity had built-in is background noise filtering; but that is easily accomplished with a plugin such as Lucian Dato's Noise Repellent.

Bertom denoiser is decent, noise repellent which can be found Here is another good one that is Foss which is a bonus aswell.