免費開源的語音辨識功能：Google Colab + Faster Whisper

!apt-get install -y libcudnn8
!pip install ctranslate2==4.3.1
!pip install onnxruntime==1.15.0
!pip install faster-whisper ipywidgets
!pip install "tokenizers>=0.13,<1"

!apt-get install -y libcudnn8
!pip install ctranslate2==4.3.1
!pip install onnxruntime==1.15.0
!pip install faster-whisper ipywidgets
!pip install "tokenizers>=0.13,<1"

from google.colab import drive
from ipywidgets import widgets, VBox, Dropdown
from IPython.display import display, clear_output
from faster_whisper import WhisperModel
import os

# 掛載 Google Drive
drive.mount('/content/drive')

# 初始化 WhisperModel
model_size = "large-v2"  # 可以根據需求調整模型大小：tiny.en, tiny, base.en, base, small.en, small, medium.en, medium, large-v1, large-v2, large-v3, large, distil-large-v2, distil-medium.en, distil-small.en, distil-large-v3, large-v3-turbo, turbo
model = WhisperModel(model_size, device="cuda", compute_type="float16")

def transcribe(audio_path, mode):
    transcription = ""
    with output:
        clear_output()
        print("正在進行語音辨識，請稍候...")
        segments, info = model.transcribe(audio_path, beam_size=5, initial_prompt="繁體")

        if mode == "normal":
            transcription_segments = [segment.text for segment in segments]
            transcription = "，".join(transcription_segments)
        elif mode == "timeline":
            for segment in segments:
                transcription += "[%.2fs -> %.2fs] %s\n" % (segment.start, segment.end, segment.text)
        elif mode == "subtitle":
          for i, segment in enumerate(segments, 1):
              start_hours, start_remainder = divmod(segment.start, 3600)
              start_minutes, start_seconds = divmod(start_remainder, 60)
              start_milliseconds = (segment.start - int(segment.start)) * 1000
              end_hours, end_remainder = divmod(segment.end, 3600)
              end_minutes, end_seconds = divmod(end_remainder, 60)
              end_milliseconds = (segment.end - int(segment.end)) * 1000
              transcription += "%d\n%02d:%02d:%02d,%03d --> %02d:%02d:%02d,%03d\n%s\n\n" % (
                  i,
                  start_hours, start_minutes, int(start_seconds), start_milliseconds,
                  end_hours, end_minutes, int(end_seconds), end_milliseconds,
                  segment.text
              )

        print("辨識完成！結果如下：")
        print(transcription)

        file_name = os.path.splitext(os.path.basename(audio_path))[0]
        with open(f"{file_name}_transcription.txt", "w") as file:
            file.write(transcription)
        print(f"辨識結果已保存為 {file_name}_transcription.txt")

        try:
            from google.colab import files
            files.download(f"{file_name}_transcription.txt")
        except ImportError:
            print("自動下載功能只在 Colab 環境中有效。")

mode_selector = Dropdown(
    options=[('一般版本', 'normal'), ('加入時間軸版本', 'timeline'), ('產生字幕檔的版本', 'subtitle')],
    value='normal',
    description='模式:',
)

file_path_input = widgets.Text(
    value='',
    placeholder='請輸入檔案路徑',
    description='檔案路徑:',
    disabled=False
)
transcribe_button = widgets.Button(
    description='進行語音辨識',
    disabled=False,
    button_style='info',
    tooltip='Click me',
    icon='check'
)
output = widgets.Output()

def on_transcribe_button_clicked(b):
    audio_path = file_path_input.value
    mode = mode_selector.value
    if os.path.exists(audio_path):
        transcribe(audio_path, mode)
    else:
        with output:
            clear_output()
            print("指定的檔案路徑不存在，請檢查！")

transcribe_button.on_click(on_transcribe_button_clicked)

clear_output()

ui = VBox([file_path_input, mode_selector, transcribe_button, output])
display(ui)