From d643aaf8a3a3fc8a31f39cb2ae3eaaf681300d4e Mon Sep 17 00:00:00 2001 From: sommerfeld Date: Wed, 13 May 2026 13:43:23 +0100 Subject: perf(dictate): switch default model to base for ~5x speedup large-v3-turbo-q5_0 ran ~1-2x realtime on the T490's CPU, making push-to-talk feel sluggish. The base multilingual model is ~142 MB (vs 547 MB) and runs ~7-10x realtime, dropping perceived latency on short utterances from a few seconds to near-instant. Quality on short EN/PT dictation remains usable; bump WHISPER_MODEL to small or large-v3-turbo if accuracy matters more than latency. --- dot_local/bin/executable_dictate | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'dot_local/bin/executable_dictate') diff --git a/dot_local/bin/executable_dictate b/dot_local/bin/executable_dictate index 2e8a361..ae8b14c 100644 --- a/dot_local/bin/executable_dictate +++ b/dot_local/bin/executable_dictate @@ -16,7 +16,7 @@ state_dir="${XDG_RUNTIME_DIR:-/tmp}/dictate" pid_file="$state_dir/pid" wav_file="$state_dir/audio.wav" log_file="$state_dir/whisper.log" -default_model='/usr/share/whisper.cpp-model-large-v3-turbo-q5_0/ggml-large-v3-turbo-q5_0.bin' +default_model='/usr/share/whisper.cpp-model-base/ggml-base.bin' model="${WHISPER_MODEL:-$default_model}" lang="${WHISPER_LANG:-auto}" @@ -34,7 +34,7 @@ start_recording() { fi if [ ! -r "$model" ]; then notify-send -u critical "🎙️ dictate" \ - "Model missing: $model. Install whisper.cpp-model-large-v3-turbo-q5_0 (AUR)." + "Model missing: $model. Install whisper.cpp-model-base (AUR)." exit 1 fi rm -f "$wav_file" -- cgit v1.3.1