def _smoke_test(self, format, compression, check_num_frames):
"""
The purpose of this test suite is to verify that apply_codec functionalities do not exhibit
abnormal behaviors.
"""
torch.random.manual_seed(42)
sample_rate = 8000
num_frames = 3 * sample_rate
num_channels = 2
waveform = torch.rand(num_channels, num_frames)
augmented = F.apply_codec(waveform, sample_rate, format, True,
compression)
assert augmented.dtype == waveform.dtype
assert augmented.shape[0] == num_channels
if check_num_frames:
assert augmented.shape[1] == num_frames
"bits_per_sample": 8
}, "8 bit mu-law"),
({
"format": "gsm"
}, "GSM-FR"),
({
"format": "mp3",
"compression": -9
}, "MP3"),
({
"format": "vorbis",
"compression": -1
}, "Vorbis"),
]
for param, title in configs:
augmented = F.apply_codec(waveform, sample_rate, **param)
plot_specgram(augmented, sample_rate, title=title)
play_audio(augmented, sample_rate)
######################################################################
# Simulating a phone recoding
# ---------------------------
#
# Combining the previous techniques, we can simulate audio that sounds
# like a person talking over a phone in a echoey room with people talking
# in the background.
#
sample_rate = 16000
speech, _ = get_speech_sample(resample=sample_rate)