Automatic Speech Recognition
WhisperKit
Core ML
Portuguese
Spanish
English
macos
apple-silicon
swift
live-captions
subtitles
speech-recognition
machine-translation
on-device
local-first
ollama
Instructions to use Veronyka/livecaption with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- WhisperKit
How to use Veronyka/livecaption with WhisperKit:
# Install CLI with Homebrew on macOS device brew install whisperkit-cli # View all available inference options whisperkit-cli transcribe --help # Download and run inference using whisper base model whisperkit-cli transcribe --audio-path /path/to/audio.mp3 # Or use your preferred model variant whisperkit-cli transcribe --model "large-v3" --model-prefix "distil" --audio-path /path/to/audio.mp3 --verbose
- Notebooks
- Google Colab
- Kaggle
Download scripts/soak.sh from Veronyka/livecaption: direct link, hf CLI and curl.
- Browser
- Download file 1.14 kB
-
https://huggingface.co/Veronyka/livecaption/resolve/main/scripts/soak.sh
- Command line
-
hf download hf://Veronyka/livecaption/scripts/soak.sh
-
curl -L -o soak.sh https://huggingface.co/Veronyka/livecaption/resolve/main/scripts/soak.sh
1.14 kB
| # Teste de resistência: alimenta o LiveCaption com tests/live_pt.f32 em tempo real por N segundos (padrão 900) | |
| # e amostra CPU/RAM do app e do Ollama. Saída em <pasta de dados>/logs: metricas-*.jsonl (do app) e soak-ps-*.csv. | |
| cd "$(dirname "$0")/.." | |
| export LC_PROJECT="${LC_PROJECT:-$HOME/Library/Application Support/LiveCaption}" | |
| mkdir -p "$LC_PROJECT/logs" | |
| DUR=${1:-900} | |
| STAMP=$(date +%Y%m%d-%H%M%S) | |
| CSV="$LC_PROJECT/logs/soak-ps-$STAMP.csv" | |
| echo "t_s,app_cpu,app_rss_mb,ollama_cpu,ollama_rss_mb,thermal" > "$CSV" | |
| LC_ALL=C LC_LOG=1 LC_WAV=$PWD/tests/live_pt.f32 LC_DURATION=$DUR ./LiveCaption.app/Contents/MacOS/LiveCaption & | |
| APP=$! | |
| caffeinate -i -w $APP & | |
| T0=$(date +%s) | |
| sleep 20 | |
| while kill -0 $APP 2>/dev/null; do | |
| A=$(LC_ALL=C ps -o %cpu=,rss= -p $APP | awk '{printf "%s,%.0f",$1,$2/1024}') | |
| O=$(LC_ALL=C ps -axo %cpu=,rss=,command= | LC_ALL=C awk '/ollama runner|ollama serve/ && !/awk/ {c+=$1; r+=$2} END {printf "%.1f,%.0f",c,r/1024}') | |
| TH=$(pmset -g therm 2>/dev/null | grep -i -E "CPU_Speed_Limit" | awk '{print $NF}') | |
| echo "$(( $(date +%s) - T0 )),$A,$O,${TH:-100}" >> "$CSV" | |
| sleep 30 | |
| done | |
| echo "fim: $CSV" | |