forked from Uberi/speech_recognition
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtest_audio.py
146 lines (125 loc) · 9.37 KB
/
test_audio.py
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
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
#!/usr/bin/env python3
import unittest
from os import path
import speech_recognition as sr
class TestAudioFile(unittest.TestCase):
def assertSimilar(self, bytes_1, bytes_2):
for i, (byte_1, byte_2) in enumerate(zip(bytes_1, bytes_2)):
if abs(byte_1 - byte_2) > 2:
raise AssertionError("{} is really different from {} at index {}".format(bytes_1, bytes_2, i))
def test_get_segment(self):
r = sr.Recognizer()
with sr.AudioFile(path.join(path.dirname(path.realpath(__file__)), "audio-mono-32-bit-44100Hz.wav")) as source: audio = r.record(source)
self.assertEqual(audio.get_raw_data(), audio.get_segment().get_raw_data())
self.assertEqual(audio.get_raw_data()[8:], audio.get_segment(0.022675738 * 2).get_raw_data())
self.assertEqual(audio.get_raw_data()[:16], audio.get_segment(None, 0.022675738 * 4).get_raw_data())
self.assertEqual(audio.get_raw_data()[8:16], audio.get_segment(0.022675738 * 2, 0.022675738 * 4).get_raw_data())
def test_wav_mono_8_bit(self):
r = sr.Recognizer()
with sr.AudioFile(path.join(path.dirname(path.realpath(__file__)), "audio-mono-8-bit-44100Hz.wav")) as source: audio = r.record(source)
self.assertIsInstance(audio, sr.AudioData)
self.assertEqual(audio.sample_rate, 44100)
self.assertEqual(audio.sample_width, 1)
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\xff\x00\xff\x00\xff\xff\x00\xff\x00\xff\x00\xff\x00\x00\xff\x00\x00\xff\x00\xff\x00\xff\x00\xff\x00\xff\x00\xff\x00\xff\xff")
def test_wav_mono_16_bit(self):
r = sr.Recognizer()
with sr.AudioFile(path.join(path.dirname(path.realpath(__file__)), "audio-mono-16-bit-44100Hz.wav")) as source: audio = r.record(source)
self.assertIsInstance(audio, sr.AudioData)
self.assertEqual(audio.sample_rate, 44100)
self.assertEqual(audio.sample_width, 2)
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\x00\xff\xff\x01\x00\xff\xff\x00\x00\x01\x00\xfe\xff\x01\x00\xfe\xff\x04\x00\xfc\xff\x04\x00\xfe\xff\xff\xff\x03\x00\xfe\xff")
def test_wav_mono_24_bit(self):
r = sr.Recognizer()
with sr.AudioFile(path.join(path.dirname(path.realpath(__file__)), "audio-mono-24-bit-44100Hz.wav")) as source: audio = r.record(source)
self.assertIsInstance(audio, sr.AudioData)
self.assertEqual(audio.sample_rate, 44100)
if audio.sample_width == 3:
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\x00\x00\x00\xff\xff\x00\x01\x00\x00\xff\xff\x00\x00\x00\x00\x01\x00\x00\xfe\xff\x00\x01\x00\x00\xfe\xff\x00\x04\x00\x00\xfb")
else:
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\x00\x00\x00\x00\x00\xff\xff\x00\x00\x01\x00\x00\x00\xff\xff\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\xfe\xff\x00\x00\x01\x00")
def test_wav_mono_32_bit(self):
r = sr.Recognizer()
audio_file_path = path.join(path.dirname(path.realpath(__file__)), "audio-mono-32-bit-44100Hz.wav")
with sr.AudioFile(audio_file_path) as source: audio = r.record(source)
self.assertIsInstance(audio, sr.AudioData)
self.assertEqual(audio.sample_rate, 44100)
self.assertEqual(audio.sample_width, 4)
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\x00\x00\x00\x00\x00\xff\xff\x00\x00\x01\x00\x00\x00\xff\xff\x00\x00\x00\x00\x00\x00\x01\x00\x00\x00\xfe\xff\x00\x00\x01\x00")
def test_wav_stereo_8_bit(self):
r = sr.Recognizer()
with sr.AudioFile(path.join(path.dirname(path.realpath(__file__)), "audio-stereo-8-bit-44100Hz.wav")) as source: audio = r.record(source)
self.assertIsInstance(audio, sr.AudioData)
self.assertEqual(audio.sample_rate, 44100)
self.assertEqual(audio.sample_width, 1)
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\xff\x00\xff\x00\x00\xff\x7f\x7f\x00\xff\x00\xff\x00\x00\xff\x00\x7f\x7f\x7f\x00\x00\xff\x00\xff\x00\xff\x00\x7f\x7f\x7f\x7f")
def test_wav_stereo_16_bit(self):
r = sr.Recognizer()
with sr.AudioFile(path.join(path.dirname(path.realpath(__file__)), "audio-stereo-16-bit-44100Hz.wav")) as source: audio = r.record(source)
self.assertIsInstance(audio, sr.AudioData)
self.assertEqual(audio.sample_rate, 44100)
self.assertEqual(audio.sample_width, 2)
self.assertSimilar(audio.get_raw_data()[:32], b"\x02\x00\xfb\xff\x04\x00\xfe\xff\xfe\xff\x07\x00\xf6\xff\x07\x00\xf9\xff\t\x00\xf5\xff\x0c\x00\xf8\xff\x02\x00\x04\x00\xfa\xff")
def test_wav_stereo_24_bit(self):
r = sr.Recognizer()
with sr.AudioFile(path.join(path.dirname(path.realpath(__file__)), "audio-stereo-24-bit-44100Hz.wav")) as source: audio = r.record(source)
self.assertIsInstance(audio, sr.AudioData)
self.assertEqual(audio.sample_rate, 44100)
if audio.sample_width == 3:
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\x00\x00\x00\xfe\xff\x00\x02\x00\x00\xfe\xff\x00\x00\x00\x00\x02\x00\x00\xfc\xff\x00\x02\x00\x00\xfc\xff\x00\x08\x00\x00\xf6")
else:
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\x00\x00\x00\x00\x00\xfe\xff\x00\x00\x02\x00\x00\x00\xfe\xff\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\xfc\xff\x00\x00\x02\x00")
def test_wav_stereo_32_bit(self):
r = sr.Recognizer()
with sr.AudioFile(path.join(path.dirname(path.realpath(__file__)), "audio-stereo-32-bit-44100Hz.wav")) as source: audio = r.record(source)
self.assertIsInstance(audio, sr.AudioData)
self.assertEqual(audio.sample_rate, 44100)
self.assertEqual(audio.sample_width, 4)
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\x00\x00\x00\x00\x00\xfe\xff\x00\x00\x02\x00\x00\x00\xfe\xff\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\xfc\xff\x00\x00\x02\x00")
def test_aiff_mono_16_bit(self):
r = sr.Recognizer()
with sr.AudioFile(path.join(path.dirname(path.realpath(__file__)), "audio-mono-16-bit-44100Hz.aiff")) as source: audio = r.record(source)
self.assertIsInstance(audio, sr.AudioData)
self.assertEqual(audio.sample_rate, 44100)
self.assertEqual(audio.sample_width, 2)
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\x00\x00\x00\xff\xff\x01\x00\xff\xff\x01\x00\xfe\xff\x02\x00\xfd\xff\x04\x00\xfc\xff\x03\x00\x00\x00\xfe\xff\x03\x00\xfd\xff")
def test_aiff_stereo_16_bit(self):
r = sr.Recognizer()
with sr.AudioFile(path.join(path.dirname(path.realpath(__file__)), "audio-stereo-16-bit-44100Hz.aiff")) as source: audio = r.record(source)
self.assertIsInstance(audio, sr.AudioData)
self.assertEqual(audio.sample_rate, 44100)
self.assertEqual(audio.sample_width, 2)
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\x00\xfe\xff\x02\x00\xfe\xff\xff\xff\x04\x00\xfa\xff\x04\x00\xfa\xff\t\x00\xf6\xff\n\x00\xfa\xff\xff\xff\x08\x00\xf5\xff")
def test_flac_mono_16_bit(self):
r = sr.Recognizer()
with sr.AudioFile(path.join(path.dirname(path.realpath(__file__)), "audio-mono-16-bit-44100Hz.flac")) as source: audio = r.record(source)
self.assertIsInstance(audio, sr.AudioData)
self.assertEqual(audio.sample_rate, 44100)
self.assertEqual(audio.sample_width, 2)
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\x00\xff\xff\x01\x00\xff\xff\x00\x00\x01\x00\xfe\xff\x02\x00\xfc\xff\x06\x00\xf9\xff\x06\x00\xfe\xff\xfe\xff\x05\x00\xfa\xff")
def test_flac_mono_24_bit(self):
r = sr.Recognizer()
with sr.AudioFile(path.join(path.dirname(path.realpath(__file__)), "audio-mono-24-bit-44100Hz.flac")) as source: audio = r.record(source)
self.assertIsInstance(audio, sr.AudioData)
self.assertEqual(audio.sample_rate, 44100)
if audio.sample_width == 3:
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\x00\x00\xff\xfe\xff\x02\x01\x00\xfd\xfe\xff\x04\x00\x00\xfc\x00\x00\x04\xfe\xff\xfb\x00\x00\x05\xfe\xff\xfc\x03\x00\x04\xfb")
else:
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\x00\x00\x00\x00\xff\xfe\xff\x00\x02\x01\x00\x00\xfd\xfe\xff\x00\x04\x00\x00\x00\xfc\x00\x00\x00\x04\xfe\xff\x00\xfb\x00\x00")
def test_flac_stereo_16_bit(self):
r = sr.Recognizer()
with sr.AudioFile(path.join(path.dirname(path.realpath(__file__)), "audio-stereo-16-bit-44100Hz.flac")) as source: audio = r.record(source)
self.assertIsInstance(audio, sr.AudioData)
self.assertEqual(audio.sample_rate, 44100)
self.assertEqual(audio.sample_width, 2)
self.assertSimilar(audio.get_raw_data()[:32], b"\xff\xff\xff\xff\x02\x00\xfe\xff\x00\x00\x01\x00\xfd\xff\x01\x00\xff\xff\x04\x00\xfa\xff\x05\x00\xff\xff\xfd\xff\x08\x00\xf6\xff")
def test_flac_stereo_24_bit(self):
r = sr.Recognizer()
with sr.AudioFile(path.join(path.dirname(path.realpath(__file__)), "audio-stereo-24-bit-44100Hz.flac")) as source: audio = r.record(source)
self.assertIsInstance(audio, sr.AudioData)
self.assertEqual(audio.sample_rate, 44100)
if audio.sample_width == 3:
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\x00\x00\x00\xfe\xff\x00\x02\x00\x00\xfe\xff\x00\x00\x00\xff\x01\x00\x02\xfc\xff\xfe\x01\x00\x02\xfc\xff\xfe\x07\x00\x01\xf6")
else:
self.assertSimilar(audio.get_raw_data()[:32], b"\x00\x00\x00\x00\x00\x00\xfe\xff\x00\x00\x02\x00\x00\x00\xfe\xff\x00\x00\x00\x00\x00\xff\x01\x00\x00\x02\xfc\xff\x00\xfe\x01\x00")
if __name__ == "__main__":
unittest.main()