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/livecaption.sh from Veronyka/livecaption: direct link, hf CLI and curl.
- Browser
- Download file 1.36 kB
-
https://huggingface.co/Veronyka/livecaption/resolve/main/scripts/livecaption.sh
- Command line
-
hf download hf://Veronyka/livecaption/scripts/livecaption.sh
-
curl -L -o livecaption.sh https://huggingface.co/Veronyka/livecaption/resolve/main/scripts/livecaption.sh
1.36 kB
| # Controle do LiveCaption: start | stop | pause | status | |
| # (pause alterna pausar/retomar; funciona de qualquer atalho: Atalhos do macOS, Keyboard Maestro, terminal...) | |
| cd "$(dirname "$0")/.." | |
| MODEL=${LC_MT_MODEL:-hymt2-1.8b} | |
| case "$1" in | |
| start) | |
| pgrep -x LiveCaption >/dev/null && { echo "já está rodando"; exit 0; } | |
| curl -s -m 2 localhost:11434/api/tags >/dev/null || { echo "iniciando Ollama…"; (ollama serve >/dev/null 2>&1 &); sleep 3; } | |
| APP=LiveCaption.app; [[ -d /Applications/LiveCaption.app ]] && APP=/Applications/LiveCaption.app | |
| open "$APP" && echo "iniciado ($APP)" ;; | |
| stop) | |
| pkill -x LiveCaption && echo "app encerrado" || echo "app não estava rodando" | |
| # libera a RAM do modelo de tradução (o servidor Ollama continua ligado, pode ter outros usos) | |
| curl -s -m 5 localhost:11434/api/generate -d "{\"model\":\"$MODEL\",\"keep_alive\":0}" >/dev/null && echo "modelo $MODEL descarregado da memória" ;; | |
| pause) | |
| pkill -USR1 -x LiveCaption && echo "pausa alternada" || echo "app não está rodando" ;; | |
| status) | |
| pgrep -x LiveCaption >/dev/null && echo "LiveCaption: rodando (pid $(pgrep -x LiveCaption))" || echo "LiveCaption: parado" | |
| curl -s -m 2 localhost:11434/api/tags >/dev/null && echo "Ollama: ativo" || echo "Ollama: parado" ;; | |
| *) echo "uso: $0 start|stop|pause|status"; exit 1 ;; | |
| esac | |