local-transcription/main_cli.py

#!/usr/bin/env python3
"""
Local Transcription CLI

Command-line version of the transcription application.
Works without GUI - perfect for testing and headless operation.
"""

import sys
import os
from pathlib import Path
import signal
import argparse

# Add project root to Python path
project_root = Path(__file__).parent
sys.path.insert(0, str(project_root))

from client.config import Config
from client.device_utils import DeviceManager
from client.transcription_engine_realtime import RealtimeTranscriptionEngine, TranscriptionResult


class TranscriptionCLI:
    """CLI transcription application."""

    def __init__(self, args):
        """Initialize the CLI application."""
        self.args = args
        self.config = Config()
        self.device_manager = DeviceManager()
        self.is_running = False

        # Override config with command-line arguments
        if args.model:
            self.config.set('transcription.model', args.model)
        if args.device:
            self.config.set('transcription.device', args.device)
        if args.language:
            self.config.set('transcription.language', args.language)
        if args.user:
            self.config.set('user.name', args.user)

        # Components
        self.transcription_engine = None

    def initialize(self):
        """Initialize all components."""
        print("=" * 60)
        print("Local Transcription CLI (RealtimeSTT)")
        print("=" * 60)

        # Device setup
        device_config = self.config.get('transcription.device', 'auto')
        self.device_manager.set_device(device_config)

        user_name = self.config.get('user.name', 'User')
        model = self.config.get('transcription.model', 'base.en')
        language = self.config.get('transcription.language', 'en')

        print(f"\nUser: {user_name}")
        print(f"Model: {model}")
        print(f"Language: {language}")
        print(f"Device: {self.device_manager.current_device}")

        # Get audio device
        audio_device_str = self.config.get('audio.input_device', 'default')
        audio_device = None if audio_device_str == 'default' else int(audio_device_str)

        # Initialize transcription engine
        print(f"\nInitializing RealtimeSTT engine...")
        device = self.device_manager.get_device_for_whisper()
        compute_type = self.config.get('transcription.compute_type', 'default')

        self.transcription_engine = RealtimeTranscriptionEngine(
            model=model,
            device=device,
            language=language,
            compute_type=compute_type,
            enable_realtime_transcription=self.config.get('transcription.enable_realtime_transcription', False),
            realtime_model=self.config.get('transcription.realtime_model', 'tiny.en'),
            silero_sensitivity=self.config.get('transcription.silero_sensitivity', 0.4),
            silero_use_onnx=self.config.get('transcription.silero_use_onnx', True),
            webrtc_sensitivity=self.config.get('transcription.webrtc_sensitivity', 3),
            post_speech_silence_duration=self.config.get('transcription.post_speech_silence_duration', 0.3),
            min_length_of_recording=self.config.get('transcription.min_length_of_recording', 0.5),
            min_gap_between_recordings=self.config.get('transcription.min_gap_between_recordings', 0.0),
            pre_recording_buffer_duration=self.config.get('transcription.pre_recording_buffer_duration', 0.2),
            beam_size=self.config.get('transcription.beam_size', 5),
            initial_prompt=self.config.get('transcription.initial_prompt', ''),
            no_log_file=True,
            input_device_index=audio_device,
            app_config=self.config
        )

        # Set up callbacks
        self.transcription_engine.set_callbacks(
            realtime_callback=self._on_realtime_transcription,
            final_callback=self._on_final_transcription
        )

        # Initialize engine (loads models, sets up VAD)
        success = self.transcription_engine.initialize()
        if not success:
            print("❌ Failed to initialize engine!")
            return False

        print("✓ Engine initialized successfully!")

        # Start recording
        success = self.transcription_engine.start_recording()
        if not success:
            print("❌ Failed to start recording!")
            return False

        print("✓ Recording started!")
        print("\n✓ All components ready!")
        return True

    def _on_realtime_transcription(self, result: TranscriptionResult):
        """Handle realtime transcription callback."""
        if self.is_running:
            print(f"[PREVIEW] {result}")

    def _on_final_transcription(self, result: TranscriptionResult):
        """Handle final transcription callback."""
        if self.is_running:
            print(f"{result}")

    def run(self):
        """Run the transcription loop."""
        if not self.initialize():
            return 1

        # Setup signal handler for graceful shutdown
        def signal_handler(sig, frame):
            print("\n\nStopping transcription...")
            self.is_running = False

        signal.signal(signal.SIGINT, signal_handler)

        print("\n" + "=" * 60)
        print("🎤 Recording... (Press Ctrl+C to stop)")
        print("=" * 60)
        print()

        # Recording is already started by the engine
        self.is_running = True

        # Keep running until interrupted
        try:
            while self.is_running:
                signal.pause()
        except AttributeError:
            # signal.pause() not available on Windows
            import time
            while self.is_running:
                time.sleep(0.1)

        # Cleanup
        self.transcription_engine.stop_recording()
        self.transcription_engine.stop()

        print("\n" + "=" * 60)
        print("✓ Transcription stopped")
        print("=" * 60)

        return 0


def main():
    """Main entry point."""
    parser = argparse.ArgumentParser(
        description='Local Transcription CLI - Real-time speech-to-text'
    )
    parser.add_argument(
        '-m', '--model',
        choices=['tiny', 'base', 'small', 'medium', 'large'],
        help='Whisper model size'
    )
    parser.add_argument(
        '-d', '--device',
        choices=['cpu', 'cuda', 'auto'],
        help='Compute device'
    )
    parser.add_argument(
        '-l', '--language',
        help='Language code (e.g., en, es, fr) or "auto"'
    )
    parser.add_argument(
        '-u', '--user',
        help='User/speaker name'
    )
    parser.add_argument(
        '--list-devices',
        action='store_true',
        help='List available audio input devices'
    )

    args = parser.parse_args()

    # List devices if requested
    if args.list_devices:
        print("Available audio input devices:")
        devices = AudioCapture.get_input_devices()
        for idx, name in devices:
            print(f"  [{idx}] {name}")
        return 0

    # Run application
    app = TranscriptionCLI(args)
    return app.run()


if __name__ == "__main__":
    sys.exit(main())