Model card: whole-process CPU share, like for like

README.md

@@ -24,8 +24,9 @@ A silence-aware, streaming end-of-turn detector for voice agents, built on Pipec
 at the VAD stop followed by a 3 s timeout, it scores the conversation every 100 ms on the CPU and
 decides at 0.2 / 0.5 / 1.2 s of silence with thresholds fitted to a false-alarm budget. On real
 multi-party conversation (AMI Meeting Corpus) it ends the turn on 5 % of mid-turn pauses where the
-stock rule fires on 42 %, and brings the 90th-percentile response time from 3.2 s to 1.3 s. It runs
-at about 9 % of one Apple M4 core single-threaded, with numpy and onnxruntime only.
+stock rule fires on 42 %, and brings the 90th-percentile response time from 3.2 s to 1.3 s. A Pipecat
+process with it takes about 17 % of one Apple M4 core against 9 % with the stock analyzer (the detector
+alone is 9 % in a tight loop); numpy and onnxruntime only.
 
 Code (Pipecat 1.14 turn analyzer, eager-then-commit stop strategy, training and evaluation):
 [github.com/OpenHRIai/smart-turn-streaming](https://github.com/OpenHRIai/smart-turn-streaming).

SHA256SUMS

@@ -1,4 +1,4 @@
-8f5e4b1f7e4dfff70198bb2867f14b75f2e3afd94944334de21ac4b9712fa29e  README.md
+0b4e5dffd9c12fd9c7dbe141fefced401a64054aaf4bfec5af766ef0ce090073  README.md
 a306d54295287307661a698d7a91e2b8c22a47413f4fba9c3e046520cf028125  LICENSE
 d52fd9c7c19eec9f0bec3107554c10937203e261259d73b01637a61501fec7f7  AMI_LICENCE.txt
 20776de499440d708a0e6703b52dfa0102ed64e83cb00565e7b2e07c22f7998c  ATTRIBUTION.md