import whisper

model = whisper.load_model("turbo", device="cuda")
result = model.transcribe("audio2.mp4", word_timestamps=False, initial_prompt="这是小学四年级习作问题诊断及指导的视频。", verbose=False, language='zh')

# result = model.transcribe("audio.mp3", word_timestamps=False, initial_prompt="这是一段小说。", verbose=False, language='zh')


def seconds_to_min_sec(total_seconds: int) -> str:
    minutes, seconds = divmod(total_seconds, 60)
    return f"{minutes}分{seconds:02d}秒"


for item in result['segments']:
    print('时间：' + str(seconds_to_min_sec(int(item['start']))) + ' ~ ' + str(
        seconds_to_min_sec(int(item['end']))) + '；' + '文本：' + str(
        item['text']))

print('所有文本内容：' + result['text'])