def metrics(deepspeech: DeepSpeech, layer_outputs: List[np.ndarray],
batch: Tuple[np.ndarray, np.ndarray]) -> Iterable[Metric]:
X, y = batch
y_hat = layer_outputs[-1]
predict_sentences = deepspeech.decode(y_hat)
true_sentences = deepspeech.get_transcripts(y)
return get_metrics(sources=predict_sentences, destinations=true_sentences)
def test_get_labels_and_get_transcripts(deepspeech: DeepSpeech):
bad_transcripts = ['to jest je$st!', 'test']
correct_transcripts = ['to jest jest', 'test']
labels = deepspeech.get_labels(bad_transcripts)
assert labels.dtype == np.int64
assert labels.shape == (2, 12)
assert labels[1, 4] == deepspeech.alphabet.blank_token
transformed_transcripts = deepspeech.get_transcripts(labels)
assert transformed_transcripts == correct_transcripts
def evaluate_batch(deepspeech: DeepSpeech, X: np.ndarray, y: np.ndarray, store: h5py.File,
references: pd.DataFrame, save_activations: bool, get_activations: Callable) -> List[Metric]:
if save_activations:
*activations, y_hat = get_activations([X, 0]) # Learning phase is `test=0`
else:
activations = []
y_hat = deepspeech.predict(X)
predict_sentences = deepspeech.decode(y_hat)
true_sentences = deepspeech.get_transcripts(y)
metrics = list(get_metrics(sources=predict_sentences, destinations=true_sentences))
save_in(store, [X, *activations, y_hat], metrics, references)
return metrics