-
-
Save panw3i/c4a9ccaba6daed4645a08984f4ded6ac to your computer and use it in GitHub Desktop.
百度语音API，包括语音转换和语音识别。
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #coding:utf-8 | |
| TEXT = "垂死病中惊坐起，笑问客从何处来" # 要转换成语音的文字 | |
| AUDIO_FILE = "./f.wav" # 要识别的语音文件 | |
| cuid = 'py' | |
| apiKey = "..." | |
| secretKey = "..." | |
| auth_url = "https://openapi.baidu.com/oauth/2.0/token?grant_type=client_credentials&client_id="\ | |
| + apiKey + "&client_secret=" + secretKey | |
| import urllib2 | |
| import json | |
| import zlib | |
| import base64 | |
| import urllib,httplib | |
| import speech_recognition as sr # pip install SpeechRecognition PyAudio | |
| def getJson(url): | |
| request = urllib2.Request(url) | |
| request.add_header('Accept-encoding', 'gzip') | |
| opener = urllib2.build_opener() | |
| response = opener.open(request) | |
| html = response.read() | |
| gzipped = response.headers.get('Content-Encoding') | |
| if gzipped: | |
| html = zlib.decompress(html, 16+zlib.MAX_WBITS) | |
| return json.loads(html) | |
| def getToken(): | |
| return getJson(auth_url)['access_token'] | |
| token = getToken() | |
| def tts(text=TEXT,file_name = "tts_result.mp3"): | |
| arr = { "tex":text, | |
| "lan":"zh", | |
| "ctp":1, | |
| "tok":token, | |
| "cuid":cuid} | |
| req = urllib2.Request(url = "http://tsn.baidu.com/text2audio",data =urllib.urlencode(arr)) | |
| res_data = urllib2.urlopen(req) | |
| res = res_data.read() | |
| with open(file_name,'wb') as f: | |
| f.write(res) | |
| def recognizer(audio_file = AUDIO_FILE): | |
| with open(audio_file, "rb") as f: | |
| data = f.read() | |
| base_date = base64.b64encode(data) | |
| arr = {"format" : "wav", | |
| "rate" : 8000, | |
| "channel": 1, | |
| "token" : "24.ec4d2760e97d8106f8e381092cc79934.2592000.1477395755.282335-4814376", | |
| "cuid" : cuid, | |
| "len" : len(data), | |
| "speech" : base_date} | |
| params = json.dumps(arr) | |
| headers = {"Content-type": "application/json"} | |
| req = urllib2.Request("http://vop.baidu.com/server_api", data=params, headers=headers) | |
| resp = urllib2.urlopen(req) | |
| data = resp.read() | |
| return data | |
| def record(file_name): | |
| r = sr.Recognizer() | |
| with sr.Microphone(sample_rate=8000) as source: # 可以指定采样率，默认16000 | |
| print("Say something!") | |
| audio = r.listen(source) | |
| with open(file_name, "wb") as f: | |
| f.write(audio.get_wav_data()) # 保存为wav | |
| if __name__ == '__main__': | |
| # record("r.wav") | |
| # tts() | |
| print recognizer("r.wav") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment