Run ASRT on smartphones. about asrt_speechrecognition HOT 7 OPEN

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"] = ""

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 = 1431
sm251bn = SpeechModel251BN(
    input_shape=(AUDIO_LENGTH, AUDIO_FEATURE_LENGTH, CHANNELS),
    output_size=OUTPUT_SIZE
)
feat = Spectrogram()
ms = ModelSpeech(sm251bn, feat, max_label_length=64)
now_path = os.path.abspath(os.getcwd())

ms.load_model(now_path+'/save_models/SpeechModel251bn_cv/' + 'SpeechModel251bn_epoch40.model.base.h5')

res = ms.recognize_speech_from_file('test1.wav')
print('*[提示] 声学模型语音识别结果：\n', res)

def load_audio(audio_path):
    from utils.ops import read_wav_data
    wav_signal, sample_rate, _, _ = read_wav_data(audio_path)
    return wav_signal, sample_rate

# load audio
from speech_features import Spectrogram
data_pre = Spectrogram()
# 使用函數直接從音訊檔案中加載音訊數據並轉換為所需的格式
audio_path = 'test1.wav'  # 替換為你的音訊檔案路徑
wav_signal, sample_rate = load_audio(audio_path)

# audio pre
# audio_features = data_pre.onnx_run(wavsignal=wav_signal, fs=sample_rate)
audio_features = data_pre.run(wavsignal=wav_signal, fs=sample_rate)
audio_features = adaptive_padding(input_data=audio_features, target_length=1600)