def _test_linearity_of_istft(self, data_size, kwargs, atol=1e-6, rtol=1e-8):
for i in range(self.number_of_trials):
tensor1 = common_utils.random_float_tensor(i, data_size)
tensor2 = common_utils.random_float_tensor(i * 2, data_size)
a, b = torch.rand(2)
istft1 = torchaudio.functional.istft(tensor1, **kwargs)
istft2 = torchaudio.functional.istft(tensor2, **kwargs)
istft = a * istft1 + b * istft2
estimate = torchaudio.functional.istft(a * tensor1 + b * tensor2, **kwargs)
self._compare_estimate(istft, estimate, atol, rtol)
def _test_istft_is_inverse_of_stft(self, kwargs):
# generates a random sound signal for each tril and then does the stft/istft
# operation to check whether we can reconstruct signal
for data_size in self.data_sizes:
for i in range(self.number_of_trials):
# Non-batch
sound = common_utils.random_float_tensor(i, data_size)
stft = torch.stft(sound, **kwargs)
estimate = torchaudio.functional.istft(stft,
length=sound.size(1),
**kwargs)
self._compare_estimate(sound, estimate)
# Batch
stft = torch.stft(sound, **kwargs)
stft = stft.repeat(3, 1, 1, 1, 1)
sound = sound.repeat(3, 1, 1)
estimate = torchaudio.functional.istft(stft,
length=sound.size(1),
**kwargs)
self._compare_estimate(sound, estimate)
def _test_istft_is_inverse_of_stft(kwargs):
# generates a random sound signal for each tril and then does the stft/istft
# operation to check whether we can reconstruct signal
for data_size in [(2, 20), (3, 15), (4, 10)]:
for i in range(100):
sound = common_utils.random_float_tensor(i, data_size)
stft = torch.stft(sound, **kwargs)
estimate = torchaudio.functional.istft(stft, length=sound.size(1), **kwargs)
_compare_estimate(sound, estimate)
