def test_dither(self):
test_filepath = common_utils.get_asset_path(
'steam-train-whistle-daniel_simon.wav')
waveform, _ = torchaudio.load(test_filepath)
waveform_dithered = F.dither(waveform)
waveform_dithered_noiseshaped = F.dither(waveform, noise_shaping=True)
E = torchaudio.sox_effects.SoxEffectsChain()
E.set_input_file(test_filepath)
E.append_effect_to_chain("dither", [])
sox_dither_waveform = E.sox_build_flow_effects()[0]
torch.testing.assert_allclose(waveform_dithered,
sox_dither_waveform,
atol=1e-04,
rtol=1e-5)
E.clear_chain()
E.append_effect_to_chain("dither", ["-s"])
sox_dither_waveform_ns = E.sox_build_flow_effects()[0]
torch.testing.assert_allclose(waveform_dithered_noiseshaped,
sox_dither_waveform_ns,
atol=1e-02,
rtol=1e-5)
def test_vctk_transform_pipeline(self):
test_filepath_vctk = os.path.join(self.test_dirpath,
"assets/VCTK-Corpus/wav48/p224/",
"p224_002.wav")
wf_vctk, sr_vctk = torchaudio.load(test_filepath_vctk)
# rate
sample = T.Resample(sr_vctk,
16000,
resampling_method='sinc_interpolation')
wf_vctk = sample(wf_vctk)
# dither
wf_vctk = F.dither(wf_vctk, noise_shaping=True)
E = torchaudio.sox_effects.SoxEffectsChain()
E.set_input_file(test_filepath_vctk)
E.append_effect_to_chain("gain", ["-h"])
E.append_effect_to_chain("channels", [1])
E.append_effect_to_chain("rate", [16000])
E.append_effect_to_chain("gain", ["-rh"])
E.append_effect_to_chain("dither", ["-s"])
wf_vctk_sox = E.sox_build_flow_effects()[0]
self.assertTrue(
torch.allclose(wf_vctk, wf_vctk_sox, rtol=1e-03, atol=1e-03))
def test_vctk_transform_pipeline(self):
test_filepath_vctk = common_utils.get_asset_path(
'VCTK-Corpus', 'wav48', 'p224', 'p224_002.wav')
wf_vctk, sr_vctk = torchaudio.load(test_filepath_vctk)
# rate
sample = T.Resample(sr_vctk,
16000,
resampling_method='sinc_interpolation')
wf_vctk = sample(wf_vctk)
# dither
wf_vctk = F.dither(wf_vctk, noise_shaping=True)
E = torchaudio.sox_effects.SoxEffectsChain()
E.set_input_file(test_filepath_vctk)
E.append_effect_to_chain("gain", ["-h"])
E.append_effect_to_chain("channels", [1])
E.append_effect_to_chain("rate", [16000])
E.append_effect_to_chain("gain", ["-rh"])
E.append_effect_to_chain("dither", ["-s"])
wf_vctk_sox = E.sox_build_flow_effects()[0]
torch.testing.assert_allclose(wf_vctk,
wf_vctk_sox,
rtol=1e-03,
atol=1e-03)
def test_dither(self):
waveform_dithered = F.dither(self.waveform_train)
waveform_dithered_noiseshaped = F.dither(self.waveform_train, noise_shaping=True)
E = torchaudio.sox_effects.SoxEffectsChain()
E.set_input_file(self.test_filepath)
E.append_effect_to_chain("dither", [])
sox_dither_waveform = E.sox_build_flow_effects()[0]
self.assertTrue(torch.allclose(waveform_dithered, sox_dither_waveform, atol=1e-04))
E.clear_chain()
E.append_effect_to_chain("dither", ["-s"])
sox_dither_waveform_ns = E.sox_build_flow_effects()[0]
self.assertTrue(torch.allclose(waveform_dithered_noiseshaped, sox_dither_waveform_ns, atol=1e-02))
def func(tensor):
return F.dither(tensor, noise_shaping=True)
def func(tensor):
return F.dither(tensor, 'GPDF')
def test_dither_noise(self):
path = get_asset_path('steam-train-whistle-daniel_simon.wav')
data, _ = load_wav(path)
result = F.dither(data, noise_shaping=True)
self.assert_sox_effect(result, path, ['dither', '-s'], atol=1.5e-4)
def test_dither(self):
path = get_asset_path('steam-train-whistle-daniel_simon.wav')
data, _ = load_wav(path)
result = F.dither(data)
self.assert_sox_effect(result, path, ['dither'])
plt.figure()
#The image is blank?? Probably matplotlib issue
plt.imshow(computed.log2()[0,:,:].detach().numpy(), cmap='gray')
# %%
#Applying gain and dithering
gain_waveform = F.gain(waveform, gain_db=5.0)
print(f'''
Min of gain_waveform: {gain_waveform.min()}
Max of gain_waveform: {gain_waveform.max()}
Mean of gain_waveform: {gain_waveform.mean()}
''')
dither_waveform = F.dither(waveform)
print(f'''
Min of dither_waveform: {dither_waveform.min()}
Max of dither_waveform: {dither_waveform.max()}
Mean of dither_waveform: {dither_waveform.mean()}
''')
# %%
#Applying filters
lowpass_waveform = F.lowpass_biquad(waveform, sample_rate, cutoff_freq=3000)
print(f'''
Min of lowpass_waveform: {lowpass_waveform.min()}
Max of lowpass_waveform: {lowpass_waveform.max()}
Mean of lowpass_waveform: {lowpass_waveform.mean()}
