def check_ctc_training(self, config, input_values, *args):
config.ctc_zero_infinity = True
model = WavLMForCTC(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_ctc_loss(self, config, input_values, *args):
model = WavLMForCTC(config=config)
model.to(torch_device)
# make sure that dropout is disabled
model.eval()
input_values = input_values[:3]
attention_mask = torch.ones(input_values.shape, device=torch_device, dtype=torch.long)
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], min(max_length_labels) - 1), model.config.vocab_size)
# pad input
for i in range(len(input_lengths)):
input_values[i, input_lengths[i] :] = 0.0
attention_mask[i, input_lengths[i] :] = 0
model.config.ctc_loss_reduction = "sum"
sum_loss = model(input_values, attention_mask=attention_mask, labels=labels).loss.item()
model.config.ctc_loss_reduction = "mean"
mean_loss = model(input_values, attention_mask=attention_mask, labels=labels).loss.item()
self.parent.assertTrue(isinstance(sum_loss, float))
self.parent.assertTrue(isinstance(mean_loss, float))
def check_labels_out_of_vocab(self, config, input_values, *args):
model = WavLMForCTC(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)