''' Author: wuxulong19950206 1287173754@qq.com Date: 2024-03-09 15:53:33 LastEditors: wuxulong19950206 1287173754@qq.com LastEditTime: 2024-03-11 20:27:11 FilePath: \ASRT_SpeechRecognition\predict_speech_file.py Description: 这是默认设置,请设置`customMade`, 打开koroFileHeader查看配置 进行设置: https://github.com/OBKoro1/koro1FileHeader/wiki/%E9%85%8D%E7%BD%AE ''' # !/usr/bin/env python3 # -*- coding: utf-8 -*- # # Copyright 2016-2099 Ailemon.net # # This file is part of ASRT Speech Recognition Tool. # # ASRT is free software: you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation, either version 3 of the License, or # (at your option) any later version. # ASRT is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with ASRT. If not, see . # ============================================================================ """ @author: nl8590687 用于通过ASRT语音识别系统预测一次语音文件的程序 """ import os from speech_model import ModelSpeech from model_zoo.speech_model.keras_backend import SpeechModel251BN from speech_features import Spectrogram from language_model3 import ModelLanguage os.environ["CUDA_VISIBLE_DEVICES"] = "0" AUDIO_LENGTH = 1600 AUDIO_FEATURE_LENGTH = 200 CHANNELS = 1 # 默认输出的拼音的表示大小是1428,即1427个拼音+1个空白块 OUTPUT_SIZE = 2884 sm251bn = SpeechModel251BN( input_shape=(AUDIO_LENGTH, AUDIO_FEATURE_LENGTH, CHANNELS), output_size=OUTPUT_SIZE ) feat = Spectrogram() ms = ModelSpeech(sm251bn, feat, max_label_length=64) ms.load_model('models\SpeechModel251bn_epoch12.model.h5') res = ms.recognize_speech_from_file('A2_1.wav') print('*[提示] 声学模型语音识别结果:\n', res) ml = ModelLanguage('model_language') ml.load_model() str_pinyin = res res = ml.pinyin_to_text(str_pinyin) print('语音识别最终结果:\n', res)