faster-whisper
===
source：https://github.com/SYSTRAN/faster-whisper

操作步驟
===
1. 安裝Visual Studio
記得勾選Python development
https://visualstudio.microsoft.com/vs/community/
2. 開啟Visual Studio新專案
3. 建立Python應用程式
4. 設定專案名稱
5. 貼上Python Script
記得變更音檔檔名(audio.mp3)、文字稿檔名(transcript.mp3)

from faster_whisper import WhisperModel

model_size = "large-v3"

# Run on GPU with FP16
# model = WhisperModel(model_size, device="cuda", compute_type="float16")

# or run on GPU with INT8
# model = WhisperModel(model_size, device="cuda", compute_type="int8_float16")
# or run on CPU with INT8
model = WhisperModel(model_size, device="cpu", compute_type="int8")

segments, info = model.transcribe("audio.mp3", beam_size=5)

print("Detected language '%s' with probability %f" % (info.language, info.language_probability))

f = open("transcript.txt", "a",encoding="utf-8")

for segment in segments:
    #print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
    f.write("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
    f.write("\n")
    
f.close()

6.點「開始」
7.畫面會提示需要安裝Python
直接安裝，有權限問題找機房人員處理
8.Python環境(右鍵)->檢視所有Python環境
9.安裝faster-whisper(PyPI套件)
10.點「開始」，等待一下子「Detected language...」會先跑出來，接著會寫入音檔文字稿(transcript.txt)，音檔長度越長等越久。