笔者正在制作少儿编程教育系列视频,发现有大量的英文视频资料值得学习,但是视频中缺少字幕,可能会对学生的学习过程带来困扰。如果能够得到英文字幕,再通过谷歌翻译等工具的使用,就可以进一步生成中文字幕。因此,开始探索快速生成字幕的方法,本文对实现过程进行记录,笔者的计算机使用的是Windows 10 64位操作系统。
注:需要计算机通过某些方法成功访问谷歌!
整体流程可划分为:
- 安装Python2
- 下载配置ffmepg
- 下载并修改autosub
- 运行命令生成视频字幕
下面依次进行展开:
- 安装Python2
这里需要安装Python2,因为后续要调用autosub,而autosub是用Python2编写的。笔者试过使用Python3,可能会需要大量的改动才能运行,最终还是按照autosub的说明安装了Python2。这里推荐下载Anaconda2进行Python2的安装,可以省去可能存在的关联包下载配置的麻烦。此外,autosub中提示安装32位Python,笔者未测试64位Python是否可行。打开下载的Anaconda2(32位)会出现:
点击“Next”:
选择“I Agree”:
笔者习惯选择“All Users”,点击“Next”:
这里推荐选择一个不含空格和中文的文件夹进行安装,比如“D:\Anaconda2”:
不建议勾选第一个选项,可能造成python不同版本间使用的混乱,比如笔者还安装了Python3。第二项默认勾选即可:
点击“Next”,安装完毕:
- 下载配置ffmepg
ffmepg主要用于解析视频内的音频。
(1)在网站“https://ffmpeg.zeranoe.com/builds/”中,下载满足操作系统要求的ffmepg版本,笔者下载的是ffmpeg-3.2-win64-static。
(2)将下载后的文件解压,将文件夹重命名为ffmepg(可选),将其整体拷贝到“D:\Anaconda2”内(拷贝到哪个目录可以灵活掌握)。
(3)将解压后文件内的“bin”目录配置到系统环境变量Path中。
首先按下Win+R键,启动运行窗口,输入sysdm.cpl:
点击确定,打开系统控制面板,然后选择高级标签:
点击环境变量,在系统变量的窗口内,找到Path:
选中Path环境变量,点击编辑。选择新建,将刚才解压得到的“bin”文件夹所在目录添加到空白处:
点击确定。到此完成ffmepg的下载和配置。
- 下载并修改autosub
autosub是用于自动生成字幕的工具,在语音转写部分调用的是Google Cloud Speech API。
(1)使用Anaconda2安装autosub
安装Anaconda2后,可以找到工具Anaconda Powershell Prompt (Anaconda2),打开后,输入:
pip install autosub
就可以完成autosub的安装。
(2)重命名autosub
autosub安装完成后文件位于“D:\Anaconda2\Scripts”内,将其重命名为“autosub_app.py”。
(3)修改autosub_app.py代码
这里对几处重点的修改展开说明,autosub_app.py的全部代码会在文末给出。
- 代码第48行,加入“, delete=False”,使临时文件不被删除,也就是将:
temp = tempfile.NamedTemporaryFile(suffix='.flac')
修改为:
temp = tempfile.NamedTemporaryFile(suffix='.flac', delete=False)
- 代码第127行,加入“.exe”,以保证成功地访问到ffmepg.exe文件,也就是将:
exe_file = os.path.join(path, program)
修改为:
exe_file = os.path.join(path, program + ".exe")
- 加入proxy信息
在引入依赖包后,添加全局proxy_dict,这里只是定义一个字典结构:
proxy_dict = {'http': 'http://127.0.0.1:8118','https': 'https://127.0.0.1:8118','use': False
}
然后修改类SpeechRecognizer,在__init__方法中加入proxy变量,在__call__方法中添加逻辑,根据命令判断是否使用proxy,发出不同的post请求。
此外,建议在抛出requests.exceptions.ConnectionError后加入一条打印提示,否则遇到连接Google服务器异常的情况,也不会提示任何错误,而程序最终会获得一个大小为0的srt字幕文件:
except requests.exceptions.ConnectionError:print "ConnectionError\n"continue
类SpeechRecognizer修改后如下:
class SpeechRecognizer(object):def __init__(self, language="en", rate=44100, retries=3, api_key=GOOGLE_SPEECH_API_KEY, proxy=proxy_dict):self.language = languageself.rate = rateself.api_key = api_keyself.retries = retriesself.proxy = proxydef __call__(self, data):try:for i in range(self.retries):url = GOOGLE_SPEECH_API_URL.format(lang=self.language, key=self.api_key)headers = {"Content-Type": "audio/x-flac; rate=%d" % self.rate}try:if self.proxy['use']:resp = requests.post(url, data=data, headers=headers, proxies=self.proxy)else:resp = requests.post(url, data=data, headers=headers)except requests.exceptions.ConnectionError:print "ConnectionError\n"continuefor line in resp.content.split("\n"):try:line = json.loads(line)line = line['result'][0]['alternative'][0]['transcript']return line[:1].upper() + line[1:]except:# no resultcontinueexcept KeyboardInterrupt:return
在main方法内加入proxy参数解析代码,这样就可以通过命令行参数来设置proxy:
parser.add_argument('-P', '--proxy', help="Set proxy server")
args = parser.parse_args()
if args.proxy:proxy_dict.update({'http': args.proxy,'https': args.proxy,'use': True
})
print("Use proxy " + args.proxy)
到此,就完成了代码的配置过程,下面就可以通过命令行,运行程序进行字幕生成了。
- 运行命令生成视频字幕
(1)代理配置信息获取(如果使用国外网络,此步可忽略)
首先需要找到计算机代理的配置信息。在win10下,右键点击桌面右下角的网络,然后打开“网络和Internet”设置,点击左侧最下方的代理:
将自动设置代理下的脚本地址,复制粘贴到浏览器地址栏内打开,拉到最下方部分,找到:
var proxy = "PROXY 127.0.0.1:8118; DIRECT;";
var direct = 'DIRECT;';
这样就能找到proxy的ip和端口设置,即127.0.0.1:8118。(根据不同工具的使用,这里的ip和端口可能会不同。)
(2)字幕提取命令
这里需要再次打开工具Anaconda Powershell Prompt (Anaconda2),将工作目录切换至包含待提取字幕视频的目录内,例如D盘根目录下有一个待提取字幕的视频“01_HowComputersWork_sm.mp4”,首先将工作目录切换至D盘,然后执行命令:
python D:\Anaconda2\Scripts\autosub_app.py -S en -D en -P http://127.0.0.1:8118 .\01_HowComputersWork_sm.mp4
如果使用国外网络,即可不配置-P及后面的参数,命令为:
python D:\Anaconda2\Scripts\autosub_app.py -S en -D en .\01_HowComputersWork_sm.mp4
运行结果如下:
程序运行最后可能会报WindowsError,笔者还没有找到解决方案,但是这并不影响程序的功能,字幕已经成功生成,可以在D盘根目录下看到“01_HowComputersWork_sm.srt”文件,打开视频导入字幕效果如下:
当然,自动生成的字幕有待进一步审核校验。
autosub_app.py代码:
#!D:\Anaconda2\python.exe
import argparse
import audioop
from googleapiclient.discovery import build
import json
import math
import multiprocessing
import os
import requests
import subprocess
import sys
import tempfile
import wavefrom progressbar import ProgressBar, Percentage, Bar, ETAfrom autosub.constants import LANGUAGE_CODES, \GOOGLE_SPEECH_API_KEY, GOOGLE_SPEECH_API_URL
from autosub.formatters import FORMATTERSproxy_dict = {'http': 'http://127.0.0.1:8118','https': 'https://127.0.0.1:8118','use': False
}def percentile(arr, percent):arr = sorted(arr)k = (len(arr) - 1) * percentf = math.floor(k)c = math.ceil(k)if f == c: return arr[int(k)]d0 = arr[int(f)] * (c - k)d1 = arr[int(c)] * (k - f)return d0 + d1def is_same_language(lang1, lang2):return lang1.split("-")[0] == lang2.split("-")[0]class FLACConverter(object):def __init__(self, source_path, include_before=0.25, include_after=0.25):self.source_path = source_pathself.include_before = include_beforeself.include_after = include_afterdef __call__(self, region):try:start, end = regionstart = max(0, start - self.include_before)end += self.include_aftertemp = tempfile.NamedTemporaryFile(suffix='.flac', delete = False)command = ["ffmpeg","-ss", str(start), "-t", str(end - start),"-y", "-i", self.source_path,"-loglevel", "error", temp.name]subprocess.check_output(command, stdin=open(os.devnull))return temp.read()except KeyboardInterrupt:returnclass SpeechRecognizer(object):def __init__(self, language="en", rate=44100, retries=3, api_key=GOOGLE_SPEECH_API_KEY, proxy=proxy_dict):self.language = languageself.rate = rateself.api_key = api_keyself.retries = retriesself.proxy = proxydef __call__(self, data):try:for i in range(self.retries):url = GOOGLE_SPEECH_API_URL.format(lang=self.language, key=self.api_key)headers = {"Content-Type": "audio/x-flac; rate=%d" % self.rate}try:if self.proxy['use']:resp = requests.post(url, data=data, headers=headers, proxies=self.proxy)else:resp = requests.post(url, data=data, headers=headers)except requests.exceptions.ConnectionError:print "ConnectionError\n"continuefor line in resp.content.split("\n"):try:line = json.loads(line)line = line['result'][0]['alternative'][0]['transcript']return line[:1].upper() + line[1:]except:# no resultcontinueexcept KeyboardInterrupt:returnclass Translator(object):def __init__(self, language, api_key, src, dst):self.language = languageself.api_key = api_keyself.service = build('translate', 'v2',developerKey=self.api_key)self.src = srcself.dst = dstdef __call__(self, sentence):try:if not sentence: returnresult = self.service.translations().list(source=self.src,target=self.dst,q=[sentence]).execute()if 'translations' in result and len(result['translations']) and \'translatedText' in result['translations'][0]:return result['translations'][0]['translatedText']return ""except KeyboardInterrupt:returndef which(program):def is_exe(fpath):return os.path.isfile(fpath) and os.access(fpath, os.X_OK)fpath, fname = os.path.split(program)if fpath:if is_exe(program):return programelse:for path in os.environ["PATH"].split(os.pathsep):path = path.strip('"')exe_file = os.path.join(path, program + ".exe")if is_exe(exe_file):return exe_filereturn Nonedef extract_audio(filename, channels=1, rate=16000):temp = tempfile.NamedTemporaryFile(suffix='.wav', delete=False)if not os.path.isfile(filename):print "The given file does not exist: {0}".format(filename)raise Exception("Invalid filepath: {0}".format(filename))if not which("ffmpeg"):print "ffmpeg: Executable not found on machine."raise Exception("Dependency not found: ffmpeg")command = ["ffmpeg", "-y", "-i", filename, "-ac", str(channels), "-ar", str(rate), "-loglevel", "error", temp.name]subprocess.check_output(command, stdin=open(os.devnull))return temp.name, ratedef find_speech_regions(filename, frame_width=4096, min_region_size=0.5, max_region_size=6):reader = wave.open(filename)sample_width = reader.getsampwidth()rate = reader.getframerate()n_channels = reader.getnchannels()total_duration = reader.getnframes() / ratechunk_duration = float(frame_width) / raten_chunks = int(total_duration / chunk_duration)energies = []for i in range(n_chunks):chunk = reader.readframes(frame_width)energies.append(audioop.rms(chunk, sample_width * n_channels))threshold = percentile(energies, 0.2)elapsed_time = 0regions = []region_start = Nonefor energy in energies:is_silence = energy <= thresholdmax_exceeded = region_start and elapsed_time - region_start >= max_region_sizeif (max_exceeded or is_silence) and region_start:if elapsed_time - region_start >= min_region_size:regions.append((region_start, elapsed_time))region_start = Noneelif (not region_start) and (not is_silence):region_start = elapsed_timeelapsed_time += chunk_durationreturn regionsdef main():parser = argparse.ArgumentParser()parser.add_argument('source_path', help="Path to the video or audio file to subtitle", nargs='?')parser.add_argument('-C', '--concurrency', help="Number of concurrent API requests to make", type=int, default=10)parser.add_argument('-o', '--output',help="Output path for subtitles (by default, subtitles are saved in \the same directory and name as the source path)")parser.add_argument('-F', '--format', help="Destination subtitle format", default="srt")parser.add_argument('-S', '--src-language', help="Language spoken in source file", default="en")parser.add_argument('-D', '--dst-language', help="Desired language for the subtitles", default="en")parser.add_argument('-K', '--api-key',help="The Google Translate API key to be used. (Required for subtitle translation)")parser.add_argument('--list-formats', help="List all available subtitle formats", action='store_true')parser.add_argument('--list-languages', help="List all available source/destination languages", action='store_true')parser.add_argument('-P', '--proxy', help="Set proxy server")args = parser.parse_args()if args.proxy:proxy_dict.update({'http': args.proxy,'https': args.proxy,'use': True})print("Use proxy " + args.proxy)if args.list_formats:print("List of formats:")for subtitle_format in FORMATTERS.keys():print("{format}".format(format=subtitle_format))return 0if args.list_languages:print("List of all languages:")for code, language in sorted(LANGUAGE_CODES.items()):print("{code}\t{language}".format(code=code, language=language))return 0if args.format not in FORMATTERS.keys():print("Subtitle format not supported. Run with --list-formats to see all supported formats.")return 1if args.src_language not in LANGUAGE_CODES.keys():print("Source language not supported. Run with --list-languages to see all supported languages.")return 1if args.dst_language not in LANGUAGE_CODES.keys():print("Destination language not supported. Run with --list-languages to see all supported languages.")return 1if not args.source_path:print("Error: You need to specify a source path.")return 1audio_filename, audio_rate = extract_audio(args.source_path)regions = find_speech_regions(audio_filename)pool = multiprocessing.Pool(args.concurrency)converter = FLACConverter(source_path=audio_filename)recognizer = SpeechRecognizer(language=args.src_language, rate=audio_rate, api_key=GOOGLE_SPEECH_API_KEY, proxy=proxy_dict)transcripts = []if regions:try:widgets = ["Converting speech regions to FLAC files: ", Percentage(), ' ', Bar(), ' ', ETA()]pbar = ProgressBar(widgets=widgets, maxval=len(regions)).start()extracted_regions = []for i, extracted_region in enumerate(pool.imap(converter, regions)):extracted_regions.append(extracted_region)pbar.update(i)pbar.finish()widgets = ["Performing speech recognition: ", Percentage(), ' ', Bar(), ' ', ETA()]pbar = ProgressBar(widgets=widgets, maxval=len(regions)).start()for i, transcript in enumerate(pool.imap(recognizer, extracted_regions)):transcripts.append(transcript)pbar.update(i)pbar.finish()if not is_same_language(args.src_language, args.dst_language):if args.api_key:google_translate_api_key = args.api_keytranslator = Translator(args.dst_language, google_translate_api_key, dst=args.dst_language,src=args.src_language)prompt = "Translating from {0} to {1}: ".format(args.src_language, args.dst_language)widgets = [prompt, Percentage(), ' ', Bar(), ' ', ETA()]pbar = ProgressBar(widgets=widgets, maxval=len(regions)).start()translated_transcripts = []for i, transcript in enumerate(pool.imap(translator, transcripts)):translated_transcripts.append(transcript)pbar.update(i)pbar.finish()transcripts = translated_transcriptselse:print "Error: Subtitle translation requires specified Google Translate API key. \See --help for further information."return 1except KeyboardInterrupt:pbar.finish()pool.terminate()pool.join()print "Cancelling transcription"return 1timed_subtitles = [(r, t) for r, t in zip(regions, transcripts) if t]formatter = FORMATTERS.get(args.format)formatted_subtitles = formatter(timed_subtitles)dest = args.outputif not dest:base, ext = os.path.splitext(args.source_path)dest = "{base}.{format}".format(base=base, format=args.format)with open(dest, 'wb') as f:f.write(formatted_subtitles.encode("utf-8"))print "Subtitles file created at {}".format(dest)os.remove(audio_filename)return 0if __name__ == '__main__':sys.exit(main())
参考链接:
https://github.com/agermanidis/autosub/issues/31
https://github.com/qq2225936589/autosub/blob/master/autosub_app.py