transcribe-server

#!/usr/bin/env bash
# Whisper transcription server — keeps the model loaded in memory.
#
# Usage:
#   transcribe-server start   # start the server (loads model)
#   transcribe-server stop    # stop the server
#   TALKTYPE_CMD="transcribe-server transcribe" talktype

SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"

# Source user config so env vars (WHISPER_MODEL, etc.) are available
# even when invoked directly (not via talktype).
TALKTYPE_CONFIG="${TALKTYPE_CONFIG:-${XDG_CONFIG_HOME:-$HOME/.config}/talktype/config}"
# shellcheck disable=SC1090
[ -f "$TALKTYPE_CONFIG" ] && source "$TALKTYPE_CONFIG"

VENV="${TALKTYPE_VENV:-$SCRIPT_DIR/.venv}"
SOCK="${XDG_RUNTIME_DIR:-/tmp}/talktype-whisper.sock"
PIDFILE="${XDG_RUNTIME_DIR:-/tmp}/talktype-whisper.pid"

WHISPER_MODEL="${WHISPER_MODEL:-base}"
WHISPER_LANG="${WHISPER_LANG:-en}"
WHISPER_DEVICE="${WHISPER_DEVICE:-cuda}"
WHISPER_COMPUTE="${WHISPER_COMPUTE:-float16}"

case "${1:-}" in
    start)
        if [ -f "$PIDFILE" ] && kill -0 "$(cat "$PIDFILE")" 2>/dev/null; then
            echo "Already running (PID $(cat "$PIDFILE"))"
            exit 0
        fi
        if [ ! -x "$VENV/bin/python3" ]; then
            echo "Whisper backend not installed. Run: make install" >&2
            exit 1
        fi
        rm -f "$PIDFILE" "$SOCK"
        echo "Starting whisper server (loading $WHISPER_MODEL model)..."
        "$VENV/bin/python3" "$SCRIPT_DIR/whisper-daemon.py" "$SOCK" "$WHISPER_MODEL" "$WHISPER_LANG" "$WHISPER_DEVICE" "$WHISPER_COMPUTE" &
        PID=$!
        disown "$PID"
        echo "$PID" > "$PIDFILE"
        for _ in $(seq 1 60); do
            [ -S "$SOCK" ] && break
            sleep 1
        done
        if [ -S "$SOCK" ]; then
            echo "Ready (PID $PID)"
        else
            echo "Failed to start" >&2
            exit 1
        fi
        ;;
    stop)
        if [ -f "$PIDFILE" ]; then
            kill "$(cat "$PIDFILE")" 2>/dev/null || true
            rm -f "$PIDFILE" "$SOCK"
            echo "Stopped"
        else
            echo "Not running"
        fi
        ;;
    transcribe)
        # Ensure daemon is alive (not just a stale socket from a crash)
        if [ -f "$PIDFILE" ] && ! kill -0 "$(cat "$PIDFILE")" 2>/dev/null; then
            rm -f "$PIDFILE" "$SOCK"
        fi
        if [ ! -S "$SOCK" ]; then
            "$0" start >&2 || exit 1
        fi
        TEXT=$(echo "$2" | socat -t 120 -T 120 - UNIX-CONNECT:"$SOCK" 2>/dev/null) || true
        if [ -z "$TEXT" ] && [ -f "$PIDFILE" ] && ! kill -0 "$(cat "$PIDFILE")" 2>/dev/null; then
            # Daemon died during transcription — restart and retry once
            rm -f "$PIDFILE" "$SOCK"
            "$0" start >&2 || exit 1
            TEXT=$(echo "$2" | socat -t 120 -T 120 - UNIX-CONNECT:"$SOCK" 2>/dev/null) || true
        fi
        printf '%s' "$TEXT"
        ;;
    *)
        echo "Usage: transcribe-server {start|stop|transcribe <audio.wav>}" >&2
        exit 1
        ;;
esac