cli.py

import argparse
import os
from speech_segmenter import SpeechSegmenter, TenVadSpeechSegmenter
from speech_to_text import SpeechToText, UtterSpeech
from subtitle_saver import SubtitleSaver

def main():
    parser = argparse.ArgumentParser(description="Generate subtitles for a video/audio file.")

    parser.add_argument("input", help="Path to the input file")

    parser.add_argument("-o", "--output", default="", help="Output file path (default: empty - so it uses the same name as the input file)")

    args = parser.parse_args()

    # Demonstration of access
    print(f"--- Configuration ---")
    print(f"Input:  {args.input}")
    print(f"Output: {args.output}")

    speech_segmenter: SpeechSegmenter = TenVadSpeechSegmenter()
    speech_to_text: SpeechToText = UtterSpeech(0)
    subtitle_saver: SubtitleSaver = SubtitleSaver()

    # Detect all speech segments.
    speech_segments = speech_segmenter.detect(args.input)

    # Transcribe all speech segments.
    transcribed_segments = speech_to_text.transcribe(speech_segments, audio_file_path=args.input)

    # Convert to subtitle file.
    subtitle_file_path = args.output
    if args.output == "":
        subtitle_file_path = os.path.basename(os.path.splitext(args.input)[0]) + ".srt"

    subtitle_saver.save(transcribed_segments, subtitle_file_path)

if __name__ == "__main__":
    main()