1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
|
"""
Audio Datasets
==============
**Author**: `Moto Hira <moto@meta.com>`__
``torchaudio`` provides easy access to common, publicly accessible
datasets. Please refer to the official documentation for the list of
available datasets.
"""
import torch
import torchaudio
print(torch.__version__)
print(torchaudio.__version__)
######################################################################
#
import os
import IPython
import matplotlib.pyplot as plt
_SAMPLE_DIR = "_assets"
YESNO_DATASET_PATH = os.path.join(_SAMPLE_DIR, "yes_no")
os.makedirs(YESNO_DATASET_PATH, exist_ok=True)
def plot_specgram(waveform, sample_rate, title="Spectrogram"):
waveform = waveform.numpy()
figure, ax = plt.subplots()
ax.specgram(waveform[0], Fs=sample_rate)
figure.suptitle(title)
figure.tight_layout()
######################################################################
# Here, we show how to use the
# :py:class:`torchaudio.datasets.YESNO` dataset.
#
dataset = torchaudio.datasets.YESNO(YESNO_DATASET_PATH, download=True)
######################################################################
#
i = 1
waveform, sample_rate, label = dataset[i]
plot_specgram(waveform, sample_rate, title=f"Sample {i}: {label}")
IPython.display.Audio(waveform, rate=sample_rate)
######################################################################
#
i = 3
waveform, sample_rate, label = dataset[i]
plot_specgram(waveform, sample_rate, title=f"Sample {i}: {label}")
IPython.display.Audio(waveform, rate=sample_rate)
######################################################################
#
i = 5
waveform, sample_rate, label = dataset[i]
plot_specgram(waveform, sample_rate, title=f"Sample {i}: {label}")
IPython.display.Audio(waveform, rate=sample_rate)
|
