def check_ctc_training(self, config, input_values, *args):
config.ctc_zero_infinity = True
model = UniSpeechSatForCTC(config=config)
model.to(torch_device)
model.train()
# freeze feature encoder
model.freeze_feature_encoder()
input_values = input_values[:3]
input_lengths = [input_values.shape[-1] // i for i in [4, 2, 1]]
max_length_labels = model._get_feat_extract_output_lengths(
torch.tensor(input_lengths))
labels = ids_tensor(
(input_values.shape[0], max(max_length_labels) - 2),
model.config.vocab_size)
# pad input
for i in range(len(input_lengths)):
input_values[i, input_lengths[i]:] = 0.0
if max_length_labels[i] < labels.shape[-1]:
# it's important that we make sure that target lenghts are at least
# one shorter than logit lenghts to prevent -inf
labels[i, max_length_labels[i] - 1:] = -100
loss = model(input_values, labels=labels).loss
self.parent.assertFalse(torch.isinf(loss).item())
loss.backward()
def check_labels_out_of_vocab(self, config, input_values, *args):
model = UniSpeechSatForCTC(config)
model.to(torch_device)
model.train()
input_values = input_values[:3]
input_lengths = [input_values.shape[-1] // i for i in [4, 2, 1]]
max_length_labels = model._get_feat_extract_output_lengths(torch.tensor(input_lengths))
labels = ids_tensor((input_values.shape[0], max(max_length_labels) - 2), model.config.vocab_size + 100)
with pytest.raises(ValueError):
model(input_values, labels=labels)
