语音合成
# coding=utf-8
import sys
import json
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
from urllib.parse import quote_plus
else:
import urllib2
from urllib import quote_plus
from urllib2 import urlopen
from urllib2 import Request
from urllib2 import URLError
from urllib import urlencode
#这里替换为自己的Key
API_KEY = 'abc'
SECRET_KEY = 'abc'
#TEXT = "欢迎使用百度语音合成。"
TEXT ="""
春晓
春眠不觉晓，处处闻啼鸟。
夜来风雨声，花落知多少。
"""
# 发音人选择, 基础音库：0为度小美，1为度小宇，3为度逍遥，4为度丫丫，
# 精品音库：5为度小娇，103为度米朵，106为度博文，110为度小童，111为度小萌，默认为度小美
PER = 110
# 语速，取值0-15，默认为5中语速
SPD = 2
# 音调，取值0-15，默认为5中语调
PIT = 5
# 音量，取值0-9，默认为5中音量
VOL = 7
# 下载的文件格式, 3：mp3(default) 4： pcm-16k 5： pcm-8k 6. wav
AUE = 3
FORMATS = {3: "mp3", 4: "pcm", 5: "pcm", 6: "wav"}
FORMAT = FORMATS[AUE]
CUID = "123456PYTHON"
TTS_URL = 'http://tsn.baidu.com/text2audio'
class DemoError(Exception):
pass
""" TOKEN start """
TOKEN_URL = 'http://openapi.baidu.com/oauth/2.0/token'
SCOPE = 'audio_tts_post' # 有此scope表示有tts能力，没有请在网页里勾选
def fetch_token():
print("fetch token begin")
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, timeout=5)
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()):
if not SCOPE in result['scope'].split(' '):
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 """
if __name__ == '__main__':
token = fetch_token()
tex = quote_plus(TEXT) # 此处TEXT需要两次urlencode
print(tex)
params = {'tok': token, 'tex': tex, 'per': PER, 'spd': SPD, 'pit': PIT, 'vol': VOL, 'aue': AUE, 'cuid': CUID,
'lan': 'zh', 'ctp': 1} # lan ctp 固定参数
data = urlencode(params)
print('test on Web Browser' + TTS_URL + '?' + data)
req = Request(TTS_URL, data.encode('utf-8'))
has_error = False
try:
f = urlopen(req)
result_str = f.read()
#pprint.pprint(headers)
headers = dict((name.lower(), value) for name, value in f.headers.items())
has_error = ('content-type' not in headers.keys() or headers['content-type'].find('audio/') < 0)
except URLError as err:
print('asr http response http code : ' + str(err.code))
result_str = err.read()
has_error = True
save_file = "error.txt" if has_error else 'result.' + FORMAT
with open(save_file, 'wb') as of:
of.write(result_str)
if has_error:
if (IS_PY3):
result_str = str(result_str, 'utf-8')
print("tts api error:" + result_str)
print("result saved as :" + save_file)
语音识别
# coding=utf-8
import sys
import json
import base64
import time
from pprint import pprint
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 = 'abc'
SECRET_KEY = 'abc'
# 需要识别的文件
AUDIO_FILE = './16k.pcm' # 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
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 """
if __name__ == '__main__':
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()
#pprint(json.loads(result_str))
#{'corpus_no': '6950929718365478897',
# 'err_msg': 'success.',
# 'err_no': 0,
# 'result': ['北京科技馆。'],
# 'sn': '25427363251618389440'}
if (IS_PY3):
result_str = str(result_str, 'utf-8')
print(result_str)
with open("result.txt","w") as of:
of.write(result_str)
