def recognize(self, wavs, fs): datapath = 'data/' modelpath = 'model_speech/' ms = ModelSpeech(datapath) ms.LoadModel(modelpath + 'speech_model22_e_0_step_6500.model') r_speech = ms.RecognizeSpeech(wavs, fs) ml = ModelLanguage('model_language') ml.LoadModel() str_pinyin = r_speech r = ml.SpeechToText(str_pinyin) return r pass
print('*[Message] Unknown System\n') datapath = 'dataset' modelpath = modelpath + '/' ms = ModelSpeech(datapath) #ms.LoadModel(modelpath + 'm22_2\\0\\speech_model22_e_0_step_257000.model') ms.LoadModel(modelpath + 'm22_2/0/speech_model22_e_0_step_257000.model') #ms.TestModel(datapath, str_dataset='test', data_count = 64, out_report = True) r = ms.RecognizeSpeech_FromFile( 'E:\语音数据集\ST-CMDS-20170001_1-OS\\20170001P00241I0052.wav') #r = ms.RecognizeSpeech_FromFile('E:\\VS2015解决方案\\wav文件读写样例\\wav文件读写样例\\bin\\Debug\\1.wav') #r = ms.RecognizeSpeech_FromFile('/home/nl/01.wav') #r = ms.RecognizeSpeech_FromFile('C:\\Users\\nl\\Desktop\\01.wav') #r = ms.RecognizeSpeech_FromFile('E:\语音数据集\ST-CMDS-20170001_1-OS\\20170001P00241I0053.wav') #r = ms.RecognizeSpeech_FromFile('E:\\语音数据集\\ST-CMDS-20170001_1-OS\\20170001P00020I0087.wav') #r = ms.RecognizeSpeech_FromFile('E:\\语音数据集\\wav\\train\\A11\\A11_167.WAV') #r = ms.RecognizeSpeech_FromFile('E:\\语音数据集\\wav\\test\\D4\\D4_750.wav') print('*[提示] 语音识别结果:\n', r) ml = ModelLanguage('model_language') ml.LoadModel() #str_pinyin = ['zhe4','zhen1','shi4','ji2', 'hao3','de5'] #str_pinyin = ['jin1', 'tian1', 'shi4', 'xing1', 'qi1', 'san1'] #str_pinyin = ['ni3', 'hao3','a1'] str_pinyin = r r = ml.SpeechToText(str_pinyin) print('语音转文字结果:\n', r)
#!/usr/bin/env python3 # encoding: utf-8 import logging import os from flask import request, Blueprint, abort, jsonify from werkzeug import secure_filename from LanguageModel import ModelLanguage from SpeechModel251 import ModelSpeech data_path = 'data/train_data/' ms = ModelSpeech(data_path) ms.LoadModel('data/speech_model/speech_model251_e_0_step_12000.model') ml = ModelLanguage('data/model_language/') ml.LoadModel() detect_speech_api = Blueprint('detect_language_api', __name__, template_folder='templates') ALLOWED_EXTENSIONS = set(['txt', 'pdf', 'png', 'jpg', 'jpeg', 'gif']) def allowed_file(filename): return '.' in filename and \ filename.rsplit('.', 1)[1] in ALLOWED_EXTENSIONS @detect_speech_api.route('/language/recognize/chinese/offline',