【完全無料】Pythonで高精度な文字お越しを無制限に行う方法

pip3 install torch torchvision torchaudio

$ nvcc -V
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on Tue_May__3_19:00:59_Pacific_Daylight_Time_2022
Cuda compilation tools, release 12.1, V11.7.64
Build cuda_12.1.r11.7/compiler.31294372_0

pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121

import torch
torch.cuda.is_available() // trueが出力されればOK

pip3 -U install faster-whisper

from faster_whisper import WhisperModel

model_size = "large-v2"
model = WhisperModel(model_size, device="cuda", compute_type="int8")

# 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")
fileName = "audio.m4a"
segments, info = model.transcribe(
  "audio.m4a", word_timestamps=True,
  initial_prompt="こんにちは、私は山田です。最後まで句読点を付けてください。",
  beam_size=5, language='ja'
)

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

with open("transcribed.txt", 'w') as f:
  for segment in segments:
    f.write( segment.text + "\n" )
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

// transcribe.py
import sys, glob, json, re

print("########## Start of character arrival ##########")

try:
    from torch import cuda
    from faster_whisper import WhisperModel
except ImportError:
    sys.stderr.write("「faster_whisper」か「pytorch」モジュールが見つかりません。\n")
    sys.exit(1)
    
mediaSourcePath = sys.argv[1]
mediaFilePath = glob.glob( f"{ mediaSourcePath }\\*" )[0]
model_size = sys.argv[2]
useLang = sys.argv[3] if sys.argv[3] else None
transcribe_results = []
plasticated_result = []

model = WhisperModel(
    model_size, compute_type="float16",
    device= 'cuda' if cuda.is_available() else 'cpu'
)
segments, info = model.transcribe(
    mediaFilePath, beam_size=5, word_timestamps=True,
    initial_prompt="こんにちは、私は山田です。Hello, I am Yamada.",
    language=useLang
)

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

for segment in segments:
    transcribe_tmp = { "start": segment.start, "end": segment.end, "subtitle": segment.text, "word_timestamps": [] }
    for word in segment.words:
        transcribe_tmp["word_timestamps"].append({ "start": word[0], "end": word[1], "text": word[2] })
    transcribe_results.append( transcribe_tmp )
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

with open( f"{ mediaSourcePath }\\transcribe.json", "w", encoding="utf-8" ) as json_file:
    json.dump( transcribe_results, json_file, indent=2, ensure_ascii=False )
    
if len( glob.glob( f"{ mediaSourcePath }\\transcribe.json" ) ) > 0:
    word_tmp, word_start_tmp, skip_flag = "", 0, False
    for transcribe in transcribe_results:
        for word in transcribe["word_timestamps"]:
            word_tmp += word["text"]
            if not skip_flag:
                word_start_tmp = word["start"]
                skip_flag = True
            if re.search( r"(\.|\?|。)$", word["text"] ):
                plasticated_result.append({
                    "start": word_start_tmp,
                    "end": word["end"], "text": re.sub( r"^\s+", "", word_tmp )
                })
                skip_flag = False
                word_tmp = ""
                
with open( f"{ mediaSourcePath }\\plasticated.json", "w", encoding="utf-8" ) as json_file:
    json.dump( plasticated_result, json_file, indent=2, ensure_ascii=False )
with open( f"{ mediaSourcePath }\\plasticated.plain.txt", mode="w", encoding="utf-8" ) as txt_file:
    for index, plasticated in enumerate( plasticated_result ):
        txt_file.write( str( index ) + ': ' + plasticated['text'] + "\n" )

$ py transcribe.py [media_source_path] [model_size] [language]

// transcribe.json
{
	{
    "start": 8.540000000000003, // 出現開始時刻（秒）
    "end": 10.88,  // 出現終了時刻
    "subtitle": " Introducing Apple Vision Pro.",  // 文字お越しされたテキスト
    "word_timestamps": [  // 更に細分化された単語ごとの情報
      {
        "start": 8.540000000000003,
        "end": 9.280000000000001,
        "text": " Introducing"
      },
      {
        "start": 9.280000000000001,
        "end": 10.02,
        "text": " Apple"
      },
      {
        "start": 10.02,
        "end": 10.42,
        "text": " Vision"
      },
      {
        "start": 10.42,
        "end": 10.88,
        "text": " Pro."
      }
    ]
  },
  {
    "start": 12.16,
    "end": 16.0,
    "subtitle": " The era of spatial computing is here.",
    "word_timestamps": [
      {
        "start": 11.870000000000001,
        "end": 12.24,
        "text": " The"
      },
      {
        "start": 12.24,
        "end": 12.62,
        "text": " era"
      },
      {
        "start": 12.62,
        "end": 12.96,
        "text": " of"
      },
      {
        "start": 12.96,
        "end": 13.28,
        "text": " spatial"
      },
      {
        "start": 13.28,
        "end": 13.8,
        "text": " computing"
      },
      {
        "start": 13.8,
        "end": 15.58,
        "text": " is"
      },
      {
        "start": 15.58,
        "end": 16.0,
        "text": " here."
      }
    ]
  },
  
  // ・・・・・・・以下省略
}

// plasticated.json
{
  {
    "start": 8.540000000000003,
    "end": 10.88,
    "text": "Introducing Apple Vision Pro."
  },
  {
    "start": 11.870000000000001,
    "end": 16.0,
    "text": "The era of spatial computing is here."
  },
  {
    "start": 22.57,
    "end": 27.38,
    "text": "When you put on Apple Vision Pro, you see your world and everything in it."
  },
  
  // ・・・・・・・以下省略
}

// srt-whisper.py
from faster_whisper import WhisperModel
import math, sys

def convert_seconds_to_hms(seconds):
    hours, remainder = divmod(seconds, 3600)
    minutes, seconds = divmod(remainder, 60)
    milliseconds = math.floor((seconds % 1) * 1000)
    output = f"{int(hours):02}:{int(minutes):02}:{int(seconds):02},{milliseconds:03}"
    return output

media_path = sys.argv[1]
language = sys.argv[2]
model_path = sys.argv[3]

model = WhisperModel(model_path, device="cuda", compute_type="int8")

segments, info = model.transcribe(
  media_path,
  initial_prompt="こんにちは、私は山田です。最後まで句読点を付けてください。",
  beam_size=5, language="ja"
)

print("Detected language '%s' with probability %f" % (info.language, info.language_probability))
count = 0
with open(media_path, 'w') as f:  # Open file for writing
  for segment in segments:
    count +=1
    duration = f"{convert_seconds_to_hms(segment.start)} --> {convert_seconds_to_hms(segment.end)}\n"
    text = f"{segment.text.lstrip()}\n\n"
    
    f.write(f"{count}\n{duration}{text}")  # Write formatted string to the file
    print(f"{duration}{text}",end='')

$ py srt-whisper.py [media_path] [language] [model_size]