You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
50 lines
1.7 KiB
50 lines
1.7 KiB
#!/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 <https://www.gnu.org/licenses/>. |
|
# ============================================================================ |
|
|
|
""" |
|
@author: nl8590687 |
|
用于测试语音识别系统语音模型的程序 |
|
""" |
|
|
|
import os |
|
|
|
from speech_model import ModelSpeech |
|
from model_zoo.speech_model.keras_backend import SpeechModel251BN |
|
from data_loader import DataLoader |
|
from speech_features import Spectrogram |
|
|
|
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 = 1428 |
|
sm251bn = SpeechModel251BN( |
|
input_shape=(AUDIO_LENGTH, AUDIO_FEATURE_LENGTH, CHANNELS), |
|
output_size=OUTPUT_SIZE |
|
) |
|
feat = Spectrogram() |
|
evalue_data = DataLoader('dev') |
|
ms = ModelSpeech(sm251bn, feat, max_label_length=64) |
|
|
|
ms.load_model('save_models/' + sm251bn.get_model_name() + '.model.h5') |
|
ms.evaluate_model(data_loader=evalue_data, data_count=-1, |
|
out_report=True, show_ratio=True, show_per_step=100)
|
|
|