| import gradio as gr | |
| from moviepy.editor import VideoFileClip | |
| import os | |
| import whisper | |
| import srt | |
| from datetime import timedelta | |
| def extract_audio(video_path): | |
| try: | |
| video = VideoFileClip(video_path) | |
| audio_path = 'audio.mp3' | |
| audio = video.audio | |
| audio.write_audiofile(audio_path) | |
| audio.close() | |
| video.close() | |
| return audio_path | |
| except Exception as e: | |
| return str(e) | |
| def transcribe_audio_to_srt(audio_path, srt_file="output.srt"): | |
| model = whisper.load_model("base.en") | |
| result = model.transcribe(audio_path) | |
| subtitles = [] | |
| for i, segment in enumerate(result['segments']): | |
| start_time = segment['start'] | |
| end_time = segment['end'] | |
| content = segment['text'].strip() | |
| subtitle = srt.Subtitle(index=i+1, | |
| start=timedelta(seconds=start_time), | |
| end=timedelta(seconds=end_time), | |
| content=content) | |
| subtitles.append(subtitle) | |
| with open(srt_file, 'w', encoding='utf-8') as f: | |
| f.write(srt.compose(subtitles)) | |
| return srt_file | |
| def process_video(video): | |
| video_path = video | |
| audio_path = extract_audio(video_path) | |
| if audio_path.endswith('.mp3'): | |
| processed_audio_path = transcribe_audio_to_srt(audio_path) | |
| with open(processed_audio_path, "r") as f: | |
| srt_content = f.read() | |
| return srt_content | |
| else: | |
| return "Failed to extract audio." | |
| iface = gr.Interface( | |
| fn=process_video, | |
| inputs=gr.Video(), | |
| outputs=gr.Textbox(label="Generated SRT File Content"), | |
| title="Extract and Process Audio from Video", | |
| description="Upload a video file to extract and process the audio, and view the generated SRT file content.", | |
| allow_flagging="never" | |
| ) | |
| iface.launch() | |