今天看到一篇很好的朗读,想把它转成文字,现知的方法有几种:
1、手机上讯飞输入法的实时语音识别。但需要人一直在旁边,需要声音外放。
2、已知的一些识别软件或者字幕软件。但找着麻烦,有的还要付费。
3、调用百度或者讯飞的接口。有好几种模式,这里采用最普通的语音识别接口,还有其他接口有待尝试。问题是坑坑巨多。
下面就3开始具体展开。
代码部分可参考百度官方示例:https://ai.baidu.com/ai-doc/SPEECH/6k38lxp0r
;https://github.com/Baidu-AIP/speech-demo。
踩得坑有这些:MP3转wav格式,wav的切割(因为普通的语音识别不支持太长的语音),wav参数的转换(采样率受代码限制,只能是16000或者8000),语音识别代码的选取(刚开始用的是谷歌的接口,在网上找了很多都是这个,但是这个总有一些奇奇怪怪的bug,开了梯子也没用)
MP3转wav格式和wav参数的转换可以通过这个软件解决:https://jingyan.baidu.com/article/c74d6000dcadee0f6a595dd2.html
wav的切割如下:`
f = wave.open(r"yu2.wav", "rb")
params = f.getparams()
anchannels, asampwidth, aframerate, anframes = params[:4]
print(aframerate)
if not aframerate == 16000:
print("采样率错误")
neirong = []
sound,shichang = get_wav_make("yu2.wav")
mm = np.linspace(0,shichang,shichang/8000)
print(shichang,mm)
for i in range(0,len(mm)-1):
begin = mm[i]
end = mm[i+1]
cut_wav = sound[begin:end] # 以毫秒为单位截取[begin, end]区间的音频
cut_wav.export("E:/py/语音转文字/分割/" + "test" + str(i)+".wav", format='wav') # 存储新的wav文件
`
全部代码:
from pydub import AudioSegment
import numpy as np
# filePath = '.../'
import sys
import json
import base64
import time
import wave
IS_PY3 = sys.version_info.major == 3
if IS_PY3:
from urllib.request import urlopen
from urllib.request import Request
from urllib.error import URLError
from urllib.parse import urlencode
timer = time.perf_counter
else:
from urllib2 import urlopen
from urllib2 import Request
from urllib2 import URLError
from urllib import urlencode
if sys.platform == "win32":
timer = time.clock
else:
# On most other platforms the best timer is time.time()
timer = time.time
API_KEY = 'yours API_KEY'
SECRET_KEY = 'yours SECRET_KEY'
CUID = '123456PYTHON'
# 采样率
RATE = 16000 # 固定值
# 普通版
DEV_PID = 1537 # 1537 表示识别普通话,使用输入法模型。根据文档填写PID,选择语言及识别模型
ASR_URL = 'http://vop.baidu.com/server_api'
SCOPE = 'audio_voice_assistant_get' # 有此scope表示有asr能力,没有请在网页里勾选,非常旧的应用可能没有
#测试自训练平台需要打开以下信息, 自训练平台模型上线后,您会看见 第二步:“”获取专属模型参数pid:8001,modelid:1234”,按照这个信息获取 dev_pid=8001,lm_id=1234
# DEV_PID = 8001 ;
# LM_ID = 1234 ;
# 极速版 打开注释的话请填写自己申请的appkey appSecret ,并在网页中开通极速版(开通后可能会收费)
# DEV_PID = 80001
# ASR_URL = 'http://vop.baidu.com/pro_api'
# SCOPE = 'brain_enhanced_asr' # 有此scope表示有极速版能力,没有请在网页里开通极速版
# 忽略scope检查,非常旧的应用可能没有
# SCOPE = False
class DemoError(Exception):
pass
""" TOKEN start """
TOKEN_URL = 'http://openapi.baidu.com/oauth/2.0/token'
def fetch_token():
params = {'grant_type': 'client_credentials',
'client_id': API_KEY,
'client_secret': SECRET_KEY}
post_data = urlencode(params)
if (IS_PY3):
post_data = post_data.encode( 'utf-8')
req = Request(TOKEN_URL, post_data)
try:
f = urlopen(req)
result_str = f.read()
except URLError as err:
# print('token http response http code : ' + str(err.code))
result_str = err.read()
if (IS_PY3):
result_str = result_str.decode()
# print(result_str)
result = json.loads(result_str)
# print(result)
if ('access_token' in result.keys() and 'scope' in result.keys()):
# print(SCOPE)
if SCOPE and (not SCOPE in result['scope'].split(' ')): # SCOPE = False 忽略检查
raise DemoError('scope is not correct')
# print('SUCCESS WITH TOKEN: %s EXPIRES IN SECONDS: %s' % (result['access_token'], result['expires_in']))
return result['access_token']
else:
raise DemoError('MAYBE API_KEY or SECRET_KEY not correct: access_token or scope not found in token response')
""" TOKEN end """
# 操作函数
def get_wav_make(dataDir):
sound = AudioSegment.from_wav(dataDir)
duration = sound.duration_seconds *10*1000 # 音频时长(ms)
# begin = 0
# end = int(duration / 2)
# cut_wav = sound[begin:end] # 以毫秒为单位截取[begin, end]区间的音频
# cut_wav.export(filePath + 'test.wav', format='wav') # 存储新的wav文件
return sound,duration
if __name__ == '__main__':
f = wave.open(r"yu2.wav", "rb")
params = f.getparams()
anchannels, asampwidth, aframerate, anframes = params[:4]
print(aframerate)
if not aframerate == 16000:
print("采样率错误")
neirong = []
sound,shichang = get_wav_make("yu2.wav")
mm = np.linspace(0,shichang,shichang/8000)
print(shichang,mm)
for i in range(0,len(mm)-1):
begin = mm[i]
end = mm[i+1]
cut_wav = sound[begin:end] # 以毫秒为单位截取[begin, end]区间的音频
cut_wav.export("E:/py/语音转文字/分割/" + "test" + str(i)+".wav", format='wav') # 存储新的wav文件
filename = "E:/py/语音转文字/分割/" + "test" + str(i)+".wav"
AUDIO_FILE = filename # 只支持 pcm/wav/amr 格式,极速版额外支持m4a 格式
# 文件格式
FORMAT = AUDIO_FILE[-3:] # 文件后缀只支持 pcm/wav/amr 格式,极速版额外支持m4a 格式
token = fetch_token()
speech_data = []
with open(AUDIO_FILE, 'rb') as speech_file:
speech_data = speech_file.read()
length = len(speech_data)
if length == 0:
raise DemoError('file %s length read 0 bytes' % AUDIO_FILE)
speech = base64.b64encode(speech_data)
if (IS_PY3):
speech = str(speech, 'utf-8')
params = {'dev_pid': DEV_PID,
# "lm_id" : LM_ID, #测试自训练平台开启此项
'format': FORMAT,
'rate': RATE,
'token': token,
'cuid': CUID,
'channel': 1,
'speech': speech,
'len': length
}
post_data = json.dumps(params, sort_keys=False)
# print post_data
req = Request(ASR_URL, post_data.encode('utf-8'))
req.add_header('Content-Type', 'application/json')
try:
begin = timer()
f = urlopen(req)
result_str = f.read()
print("Request time cost %f" % (timer() - begin))
except URLError as err:
print('asr http response http code : ' + str(err.code))
result_str = err.read()
if (IS_PY3):
result_str = str(result_str, 'utf-8')
print(result_str)
neirong.append(result_str)
time.sleep(0.2)
时间匆忙,万望海涵。有事请私信,谢谢。