test: add isolated realtime STT adoption probe - #503
Draft
TheAngryPit wants to merge 1 commit into
Draft
TheAngryPit wants to merge 1 commit into
TheAngryPit wants to merge 1 commit into
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Refs #499. Depends on Blaizzy/mlx-audio#945 and Blaizzy/mlx-vlm#2167.
The existing Nativ Python overlay already exposes the new upstream route once the candidate packages are present. This PR adds a reproducible isolated loopback WebSocket probe and candidate adoption documentation instead of mounting a second server or changing production dependency pins.
Verified the actual Nativ overlay with real local Nemotron 3.5 0.6B weights and paced 20ms synthetic PCM in Portuguese and English. Both produced partial text before commit and final transcripts afterwards. Probe observations: PT first partial 2.717s, commit-to-final 0.249s; EN 1.636s and 0.295s. These are single-run observations, not latency percentiles.
The probe uses an ephemeral loopback port and isolated temporary analytics, offline local weights, and stops its server. No installed app, production configuration or model cache was modified. Full distribution packaging and microphone/UI proof remain separate and unverified. Kept draft pending upstream dependency availability.