def specaug_fbank_test():
conf = {
"feature_type": "fbank",
"sample_rate": 16000,
"num_mel_bins": 80,
"use_energy": False,
"spec_aug": {
"freq_mask_num": 2,
"freq_mask_width": 27,
"time_mask_num": 2,
"time_mask_width": 100,
}
}
fn = "file:testdata/100-121669-0000.wav"
pipe = "pipe:flac -c -d -s testdata/103-1240-0005.flac |"
sample_rate, waveform1 = utils.load_wave(fn)
sample_rate, waveform2 = utils.load_wave(pipe)
waveform1 = torch.from_numpy(waveform1)
waveform2 = torch.from_numpy(waveform2)
lengths = [waveform1.shape[0], waveform2.shape[0]]
max_length = max(lengths)
print(lengths)
padded_waveforms = torch.zeros(2, max_length)
padded_waveforms[0, :lengths[0]] += waveform1
padded_waveforms[1, :lengths[1]] += waveform2
layer = SPLayer(conf)
features, feature_lengths = layer(padded_waveforms, lengths)
import matplotlib as mpl
mpl.use('Agg')
import matplotlib.pyplot as plt
plt.imshow(features[1].numpy())
plt.savefig("test.png")
def get_dur(wav_dic):
durdic = {}
for key, path in wav_dic.items():
sample_rate, data = utils.load_wave(path)
dur = data.shape[0] / float(sample_rate)
durdic[key] = dur
return durdic
def __getitem__(self, idx):
if self.feature_type == "waveform":
path, label = self.item[idx]
return (load_wave(path), label)
else:
path, label = self.item[idx]
feature = torch.FloatTensor(read_ark(path))
if self.mel:
return (F_Mel(feature, audio_conf), label)
else:
return (feature, label)
def load_wave_batch(paths):
waveforms = []
lengths = []
for path in paths:
sample_rate, waveform = utils.load_wave(path)
waveform = torch.from_numpy(waveform)
waveforms.append(waveform)
lengths.append(waveform.shape[0])
max_length = max(lengths)
padded_waveforms = torch.zeros(len(lengths), max_length)
for i in range(len(lengths)):
padded_waveforms[i, :lengths[i]] += waveforms[i]
return padded_waveforms, torch.tensor(lengths).long()
def specaug_test():
featconf = {
"feature_type": "fbank",
"sample_rate": 16000,
"num_mel_bins": 40,
"use_energy": False
}
augconf = {
"feature_type": "fbank",
"sample_rate": 16000,
"num_mel_bins": 40,
"use_energy": False,
"spec_aug": {
"freq_mask_width": 10,
"freq_mask_num": 2,
"time_mask_width": 100,
"time_mask_num": 2
}
}
fn = "file:testdata/100-121669-0000.wav"
pipe = "pipe:flac -c -d -s testdata/103-1240-0005.flac |"
sample_rate, waveform1 = utils.load_wave(fn)
sample_rate, waveform2 = utils.load_wave(pipe)
waveform1 = torch.from_numpy(waveform1)
waveform2 = torch.from_numpy(waveform2)
lengths = [waveform1.shape[0], waveform2.shape[0]]
max_length = max(lengths)
padded_waveforms = torch.zeros(2, max_length)
padded_waveforms[0, :lengths[0]] += waveform1
padded_waveforms[1, :lengths[1]] += waveform2
splayer = SPLayer(featconf)
auglayer = SPLayer(augconf)
features, feature_lengths = splayer(padded_waveforms, lengths)
features2, feature_lengths2 = auglayer(padded_waveforms, lengths)
print("Before augmentation")
print(features)
print("After augmentation")
print(features2)
def test_load_wave():
pipe = "pipe:flac -c -d -s testdata/100-121669-0000.flac | "
fn = "file:testdata/100-121669-0000.wav"
ark = "ark:/data1/Corpora/LibriSpeech/ark/train_960.ark:16"
ark2 = "ark:/data1/Corpora/LibriSpeech/ark/train_960.ark:2591436"
timer = utils.Timer()
timer.tic()
s3, d3 = utils.load_wave(ark)
print("Load ark time: {}s".format(timer.toc()))
timer.tic()
s2, d2 = utils.load_wave(fn)
print("Load file time: {}s".format(timer.toc()))
timer.tic()
s1, d1 = utils.load_wave(pipe)
print("Load flac pipe time: {}s".format(timer.toc()))
print("Load ark2")
s, d = utils.load_wave(ark2)
assert s1 == s2
assert s3 == s2
assert np.sum(d1 != d2) == 0
assert np.sum(d3 != d2) == 0
def fbank_test():
conf = {
"feature_type": "fbank",
"sample_rate": 16000,
"num_mel_bins": 40,
"use_energy": False
}
fn = "file:testdata/100-121669-0000.wav"
pipe = "pipe:flac -c -d -s testdata/103-1240-0005.flac |"
sample_rate, waveform1 = utils.load_wave(fn)
sample_rate, waveform2 = utils.load_wave(pipe)
waveform1 = torch.from_numpy(waveform1)
waveform2 = torch.from_numpy(waveform2)
lengths = [waveform1.shape[0], waveform2.shape[0]]
max_length = max(lengths)
padded_waveforms = torch.zeros(2, max_length)
padded_waveforms[0, :lengths[0]] += waveform1
padded_waveforms[1, :lengths[1]] += waveform2
layer = SPLayer(conf)
features, feature_lengths = layer(padded_waveforms, lengths)
print(features)
print(feature_lengths)
def decode_file():
start = time.time_ns()
get_wave = utils.load_wave(save_base='../receive', file_name='output.wav')
end = time.time_ns()
print('读取文件耗时：', (end - start) / 1e6, 'ms')
if len(get_wave.shape) == 2:
get_wave = get_wave[:, 0]
start = time.time_ns()
packets = FSK.demodulation(utils.init_args(), get_wave)
count, result = utils.decode_bluetooth_packet(utils.init_args(), packets)
f = open('../result.txt', 'w', encoding='utf-8')
f.write(result)
f.close()
end = time.time_ns()
print('解码文本耗时：', (end - start) / 1e6, 'ms')
print('蓝牙包成功解码数量：{}\n解码信息：{}\n'.format(count, result))
def get_result(self):
'''
描述：解析并获取录音结果
参数：无
返回：无
'''
get_wave = load_wave(save_base=args.save_base_receive,
file_name=self.save_place)
wave = bandpass(get_wave, self.args.framerate,
self.args.frequency - 500, self.args.frequency + 500)
#get_wave = filt_wave(get_wave)
get_seq = pulse_demodulation(wave, args)
print(get_seq)
result = decode(get_seq)
decode_original = decode(self.original_seq)
#计算传输速率，丢包率，准确率
speed = len(
self.original_seq) / (len(get_wave) / self.args.framerate) / 8
packet_loss = max(0, (len(decode_original) - len(result)) /
len(decode_original))
show_text = "原始结果：{}\n接收结果：{} \n传输速率：{:.2f}byte/s\n丢包率：{:.2f}%\n".format(
decode_original, result, speed, 100 * packet_loss)
tkinter.messagebox.showinfo('传输结果', show_text)
parser.add_argument("--nchannels", type=int, default=1)
parser.add_argument("--volume", type=float, default=1.0)
parser.add_argument("--start_place", type=int, default=0)
parser.add_argument("--pulse_length", type=float, default=0.01)
parser.add_argument("--interval_0", type=float, default=0.01)
parser.add_argument("--interval_1", type=float, default=0.02)
parser.add_argument("--save_base", type=str, default='sound')
parser.add_argument("--file_name", type=str, default='pulse.wav')
parser.add_argument("--seq_len", type=int, default=100)
args = parser.parse_args()
original_seq = generate_random_seq(args.seq_len)
print("The original seq is:\n", original_seq)
the_wave = pulse_modulation(original_seq, args)
save_wave(the_wave,
framerate=args.framerate,
sample_width=args.sample_width,
nchannels=args.nchannels,
save_base=args.save_base,
file_name=args.file_name)
get_wave = load_wave(save_base=args.save_base, file_name=args.file_name)
get_seq = pulse_demodulation(get_wave, args)
print("The loaded seq is:\n", get_seq)
result = compare_seqs(original_seq, get_seq)
if result:
print("The original seq and the seq I get is identical, right!")
else:
print("The original seq and the seq I get is not identical, wrong!")
def main():
packets = FSK.demodulation(utils.init_args(),
utils.load_wave("", "_tmp_a_0_6535.wav"))
