From: Anderson A. Giacomolli <redacted>
Date: Wed, 11 Nov 2026 02:07:16 +0000 (-0300)
Subject: Benchmark local voice transcription
X-Git-Url: https://git.giacomolli.uk/onechat/commitdiff_plain/23d56510bff3cda373977f2e85360b2d4ef8e7e2?hp=23d56510bff3cda373977f2e85360b2d4ef8e7e2

Benchmark local voice transcription

A separate Nix package compares two pinned Whisper models on public
English and Portuguese Ogg Opus excerpts. It prints each transcript,
wall time, and peak memory so the local voice model can be selected
without an external service or private audio. A decode probe selects 16
kHz mono WAV conversion when direct Opus input is not supported.
---