Python ModelSpeech示例

示例#1

    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

示例#2

文件： test.py 项目： huanzoey/ASRT_SpeechRecognition

datapath = ''
modelpath = 'model_speech'

system_type = plat.system()  # 由于不同的系统的文件路径表示不一样，需要进行判断
if (system_type == 'Windows'):
    datapath = 'E:\\语音数据集'
    modelpath = modelpath + '\\'
elif (system_type == 'Linux'):
    datapath = 'dataset'
    modelpath = modelpath + '/'
else:
    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)

示例#3

if(not os.path.exists(modelpath)): # 判断保存模型的目录是否存在
	os.makedirs(modelpath) # 如果不存在，就新建一个，避免之后保存模型的时候炸掉

system_type = plat.system() # 由于不同的系统的文件路径表示不一样，需要进行判断
if(system_type == 'Windows'):
	datapath = 'E:\\语音数据集'
	modelpath = modelpath + '\\'
elif(system_type == 'Linux'):
	datapath = 'dataset'
	modelpath = modelpath + '/'
else:
	print('*[Message] Unknown System\n')
	datapath = 'dataset'
	modelpath = modelpath + '/'

ms = ModelSpeech(datapath)

ms.LoadModel(modelpath + 'm22_2\\2\\speech_model22_e_0_step_123500.model')

ms.TestModel(datapath, str_dataset='test', data_count = 128, out_report = True)

#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)

示例#4

文件： train_mspeech.py 项目： wuwei3017/ASRT_SpeechRecognition

os.environ["CUDA_VISIBLE_DEVICES"] = "0"
#进行配置，使用70%的GPU
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.9
#config.gpu_options.allow_growth=True   #不全部占满显存, 按需分配
set_session(tf.Session(config=config))

datapath = ''
modelpath = 'model_speech'

if (not os.path.exists(modelpath)):  # 判断保存模型的目录是否存在
    os.makedirs(modelpath)  # 如果不存在，就新建一个，避免之后保存模型的时候炸掉

system_type = plat.system()  # 由于不同的系统的文件路径表示不一样，需要进行判断
if (system_type == 'Windows'):
    datapath = 'E:\\语音数据集'
    modelpath = modelpath + '\\'
elif (system_type == 'Linux'):
    datapath = 'dataset'
    modelpath = modelpath + '/'
else:
    print('*[Message] Unknown System\n')
    datapath = 'dataset'
    modelpath = modelpath + '/'

ms = ModelSpeech(datapath)

#ms.LoadModel(modelpath + 'speech_model22_e_0_step_327500.model')
ms.TrainModel(datapath, epoch=50, batch_size=4, save_step=500)

示例#5

datapath = ''
modelpath = 'model_speech'

system_type = plat.system()  # 由于不同的系统的文件路径表示不一样，需要进行判断
if (system_type == 'Windows'):
    datapath = 'E:\\语音数据集'
    modelpath = modelpath + '\\'
elif (system_type == 'Linux'):
    datapath = 'dataset'
    modelpath = modelpath + '/'
else:
    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 + 'speech_model22_e_0_step_317000.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:\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()

示例#6

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
@author: nl8590687
语音识别API的HTTP服务器程序

"""
import http.server
import urllib
import keras
from SpeechModel22 import ModelSpeech
from LanguageModel import ModelLanguage

datapath = 'data/'
modelpath = 'model_speech/'
ms = ModelSpeech(datapath)
ms.LoadModel(modelpath + 'speech_model22_e_0_step_216500.model')

ml = ModelLanguage('model_language')
ml.LoadModel()


class TestHTTPHandle(http.server.BaseHTTPRequestHandler):
    def _set_response(self):
        self.send_response(200)
        self.send_header('Content-type', 'text/html')
        self.end_headers()

    def do_GET(self):

        buf = 'ASRT_SpeechRecognition API'

示例#7

文件： test_mspeech.py 项目： wuwei3017/ASRT_SpeechRecognition

if(not os.path.exists(modelpath)): # 判断保存模型的目录是否存在
	os.makedirs(modelpath) # 如果不存在，就新建一个，避免之后保存模型的时候炸掉

system_type = plat.system() # 由于不同的系统的文件路径表示不一样，需要进行判断
if(system_type == 'Windows'):
	datapath = 'E:\\语音数据集'
	modelpath = modelpath + '\\'
elif(system_type == 'Linux'):
	datapath = 'dataset'
	modelpath = modelpath + '/'
else:
	print('*[Message] Unknown System\n')
	datapath = 'dataset'
	modelpath = modelpath + '/'

ms = ModelSpeech(datapath)

ms.LoadModel(modelpath + 'speech_model22_e_0_step_327500.model')

ms.TestModel(datapath, str_dataset='train', data_count = 128, out_report = True)

#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)