基于语音识别接口智能语音识别和字幕推荐系统-深度学习算法应用（含全部工程源码）+测试数据集

from moviepy.editor import AudioFileClip from pydub import AudioSegment from pydub.silence import detect_silence from aip import AipSpeech import os import time import re import requests import js2py class baidu_Translate(): def __init__(self): self.js = js2py.eval_js(''' var i = null; function n(r, o) { for (var t = 0; t < o.length - 2; t += 3) { var a = o.charAt(t + 2); a = a >= "a" ? a.charCodeAt(0) - 87 : Number(a), a = "+" === o.charAt(t + 1) ? r >>> a: r << a, r = "+" === o.charAt(t) ? r + a & 4294967295 : r ^ a } return r } var hash = function e(r,gtk) { var o = r.match(/[\uD800-\uDBFF][\uDC00-\uDFFF]/g); if (null === o) { var t = r.length; t > 30 && (r = "" + r.substr(0, 10) + r.substr(Math.floor(t / 2) - 5, 10) + r.substr( - 10, 10)) } else { for (var e = r.split(/[\uD800-\uDBFF][\uDC00-\uDFFF]/), C = 0, h = e.length, f = []; h > C; C++)"" !== e[C] && f.push.apply(f, a(e[C].split(""))), C !== h - 1 && f.push(o[C]); var g = f.length; g > 30 && (r = f.slice(0, 10).join("") + f.slice(Math.floor(g / 2) - 5, Math.floor(g / 2) + 5).join("") + f.slice( - 10).join("")) } var u = void 0, u = null !== i ? i: (i = gtk || "") || ""; for (var d = u.split("."), m = Number(d[0]) || 0, s = Number(d[1]) || 0, S = [], c = 0, v = 0; v < r.length; v++) { var A = r.charCodeAt(v); 128 > A ? S[c++] = A: (2048 > A ? S[c++] = A >> 6 | 192 : (55296 === (64512 & A) && v + 1 < r.length && 56320 === (64512 & r.charCodeAt(v + 1)) ? (A = 65536 + ((1023 & A) << 10) + (1023 & r.charCodeAt(++v)), S[c++] = A >> 18 | 240, S[c++] = A >> 12 & 63 | 128) : S[c++] = A >> 12 | 224, S[c++] = A >> 6 & 63 | 128), S[c++] = 63 & A | 128) } for ( var p = m,F = "+-a^+6", D = "+-3^+b+-f", b = 0; b < S.length; b++) p += S[b],p = n(p, F); return p = n(p, D), p ^= s, 0 > p && (p = (2147483647 & p) + 2147483648), p %= 1e6, p.toString() + "." + (p ^ m) } ''') headers = { 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.96 Safari/537.36', } self.session = requests.Session() self.session.get('https://fanyi.baidu.com', headers=headers) response = self.session.get('https://fanyi.baidu.com', headers=headers) self.token = re.findall("token: '(.*?)',", response.text)[0] self.gtk = '320305.131321201' # re.findall("window.gtk = '(.*?)';", response.text, re.S)[0] def translate(self, query, from_lang='en', to_lang='zh'): # langdetect self.session.post('https://fanyi.baidu.com/langdetect', data={'query': query}) # clickEvent self.session.get('https://click.fanyi.baidu.com/?src=1&locate=zh&action=query&type=1&page=1') # translate data = { 'from': from_lang, 'to': to_lang, 'query': query, 'transtype': 'realtime', 'simple_means_flag': '3', 'sign': self.js(query, self.gtk), 'token': self.token } response = self.session.post('https://fanyi.baidu.com/v2transapi', data=data) json = response.json() if 'error' in json: pass # return 'error: {}'.format(json['error']) else: return response.json()['trans_result']['data'][0]['dst'] class baidu_SpeechRecognition(): def __init__(self, dev_pid): # 百度语音识别API Speech_APP_ID = '19712136' Speech_API_KEY = 'Loo4KbNtagchc2BLdCnHEnZl' Speech_SECRET_KEY = 'DO4UlSnw7FzpodU2G3yXQSHLv6Q2inN8' self.dev_pid = dev_pid self.SpeechClient = AipSpeech(Speech_APP_ID, Speech_API_KEY, Speech_SECRET_KEY) self.TranslClient = baidu_Translate() def load_audio(self, audio_file): self.source = AudioSegment.from_wav(audio_file) def speech_recognition(self, offset, duration, fanyi): data = self.source[offset * 1000:duration * 1000].raw_data result = self.SpeechClient.asr(data, 'wav', 16000, {'dev_pid': self.dev_pid, }) fanyi_text = '' if fanyi: try: fanyi_text = self.TranslClient.translate(result['result'][0]) except: pass try: return [result['result'][0], fanyi_text] except: # print('错误:',result) return ['', ''] def cut_point(path, dbfs=1.25): sound = AudioSegment.from_file(path, format="wav") tstamp_list = detect_silence(sound, 600, sound.dBFS * dbfs, 1) timelist = [] for i in range(len(tstamp_list)): if i == 0: back = 0 else: back = tstamp_list[i - 1][1] / 1000 timelist.append([back, tstamp_list[i][1] / 1000]) min_len = 0.5 max_len = 5 result = [] add = 0 total = len(timelist) for x in range(total): if x + add < total: into, out = timelist[x + add] if out - into > min_len and out - into < max_len and x + add + 1 < total: add += 1 out = timelist[x + add][1] result.append([into, out]) elif out - into > max_len: result.append([into, out]) else: break return result def cut_text(text, length=38): newtext = '' if len(text) > length: while True: cutA = text[:length] cutB = text[length:] newtext += cutA + '\n' if len(cutB) < 4: newtext = cutA + cutB break elif len(cutB) > length: text = cutB else: newtext += cutB break return newtext return text def progressbar(total, temp, text='&&', lenght=40): content = '\r' + text.strip().replace('&&', '[{0}{1}]{2}%') percentage = round(temp / total * 100, 2) a = round(temp / total * lenght) b = lenght - a print(content.format('■' * a, '□' * b, percentage), end='') def format_time(seconds): sec = int(seconds) m, s = divmod(sec, 60) h, m = divmod(m, 60) fm = int(str(round(seconds, 3)).split('.')[-1]) return "%02d:%02d:%02d,%03d" % (h, m, s, fm) def separate_audio(file_path, save_path): audio_file = save_path + '\\tmp.wav' audio = AudioFileClip(file_path) audio.write_audiofile(audio_file, ffmpeg_params=['-ar', '16000', '-ac', '1'], logger=None) return audio_file def file_filter(path, alldir=False): key = ['mp4', 'mov'] if alldir: dic_list = os.walk(path) else: dic_list = os.listdir(path) find_list = [] for i in dic_list: if os.path.isdir(i[0]): header = i[0] file = i[2] for f in file: for k in key: if f.rfind(k) != -1: find_list.append([header, f]) else: for k in key: if i.rfind(k) != -1: find_list.append([path, i]) if find_list: find_list.sort(key=lambda txt: re.findall(r'\d+', txt[1])[0]) return find_list def countTime(s_time, now=True): if now: s_time = (time.time() - s_time) m, s = divmod(int(s_tim