diff options
| -rw-r--r-- | dot_local/bin/executable_dictate | 4 | ||||
| -rw-r--r-- | meta/extra.txt | 4 |
2 files changed, 5 insertions, 3 deletions
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" diff --git a/meta/extra.txt b/meta/extra.txt index fb87c3d..36c311f 100644 --- a/meta/extra.txt +++ b/meta/extra.txt @@ -10,5 +10,7 @@ tesseract-data-eng tesseract-data-por # Speech-to-text (used by ~/.local/bin/dictate) +# `base` multilingual: ~142 MB, ~7-10x realtime on a 4c CPU. Override +# WHISPER_MODEL in the script's environment to use a different ggml model. whisper.cpp -whisper.cpp-model-large-v3-turbo-q5_0 +whisper.cpp-model-base |