diff --git a/datasets/librispeech/librispeech.py b/datasets/librispeech/librispeech.py index 422b1ed8..d963a7d5 100644 --- a/datasets/librispeech/librispeech.py +++ b/datasets/librispeech/librispeech.py @@ -16,8 +16,8 @@ import tarfile import argparse import soundfile import json -from paddle.v2.dataset.common import md5file import codecs +from paddle.v2.dataset.common import md5file DATA_HOME = os.path.expanduser('~/.cache/paddle/dataset/speech') diff --git a/error_rate.py b/error_rate.py index 22e5c19b..ea829f47 100644 --- a/error_rate.py +++ b/error_rate.py @@ -41,15 +41,17 @@ def _levenshtein_distance(ref, hyp): # calculate levenshtein distance for i in xrange(1, m + 1): - distance[i % 2][0] = i + prev_row_idx = (i - 1) % 2 + cur_row_idx = i % 2 + distance[cur_row_idx][0] = i for j in xrange(1, n + 1): if ref[i - 1] == hyp[j - 1]: - distance[i % 2][j] = distance[(i - 1) % 2][j - 1] + distance[cur_row_idx][j] = distance[prev_row_idx][j - 1] else: - s_num = distance[(i - 1) % 2][j - 1] + 1 - i_num = distance[i % 2][j - 1] + 1 - d_num = distance[(i - 1) % 2][j] + 1 - distance[i % 2][j] = min(s_num, i_num, d_num) + s_num = distance[prev_row_idx][j - 1] + 1 + i_num = distance[cur_row_idx][j - 1] + 1 + d_num = distance[prev_row_idx][j] + 1 + distance[cur_row_idx][j] = min(s_num, i_num, d_num) return distance[m % 2][n] diff --git a/tests/test_error_rate.py b/tests/test_error_rate.py index 370dd0da..99e137a9 100644 --- a/tests/test_error_rate.py +++ b/tests/test_error_rate.py @@ -11,16 +11,54 @@ import error_rate class TestParse(unittest.TestCase): def test_wer_1(self): ref = 'i UM the PHONE IS i LEFT THE portable PHONE UPSTAIRS last night' - hyp = 'i GOT IT TO the FULLEST i LOVE TO portable FROM OF STORES last night' + hyp = 'i GOT IT TO the FULLEST i LOVE TO portable FROM OF STORES last '\ + 'night' word_error_rate = error_rate.wer(ref, hyp) self.assertTrue(abs(word_error_rate - 0.769230769231) < 1e-6) def test_wer_2(self): + ref = 'as any in england i would say said gamewell proudly that is '\ + 'in his day' + hyp = 'as any in england i would say said came well proudly that is '\ + 'in his day' + word_error_rate = error_rate.wer(ref, hyp) + self.assertTrue(abs(word_error_rate - 0.1333333) < 1e-6) + + def test_wer_3(self): + ref = 'the lieutenant governor lilburn w boggs afterward governor '\ + 'was a pronounced mormon hater and throughout the period of '\ + 'the troubles he manifested sympathy with the persecutors' + hyp = 'the lieutenant governor little bit how bags afterward '\ + 'governor was a pronounced warman hater and throughout the '\ + 'period of th troubles he manifests sympathy with the '\ + 'persecutors' + word_error_rate = error_rate.wer(ref, hyp) + self.assertTrue(abs(word_error_rate - 0.2692307692) < 1e-6) + + def test_wer_4(self): + ref = 'the wood flamed up splendidly under the large brewing copper '\ + 'and it sighed so deeply' + hyp = 'the wood flame do splendidly under the large brewing copper '\ + 'and its side so deeply' + word_error_rate = error_rate.wer(ref, hyp) + self.assertTrue(abs(word_error_rate - 0.2666666667) < 1e-6) + + def test_wer_5(self): + ref = 'all the morning they trudged up the mountain path and at noon '\ + 'unc and ojo sat on a fallen tree trunk and ate the last of '\ + 'the bread which the old munchkin had placed in his pocket' + hyp = 'all the morning they trudged up the mountain path and at noon '\ + 'unc in ojo sat on a fallen tree trunk and ate the last of '\ + 'the bread which the old munchkin had placed in his pocket' + word_error_rate = error_rate.wer(ref, hyp) + self.assertTrue(abs(word_error_rate - 0.027027027) < 1e-6) + + def test_wer_6(self): ref = 'i UM the PHONE IS i LEFT THE portable PHONE UPSTAIRS last night' word_error_rate = error_rate.wer(ref, ref) self.assertEqual(word_error_rate, 0.0) - def test_wer_3(self): + def test_wer_7(self): ref = ' ' hyp = 'Hypothesis sentence' with self.assertRaises(ValueError): @@ -39,28 +77,34 @@ class TestParse(unittest.TestCase): self.assertTrue(abs(char_error_rate - 0.125) < 1e-6) def test_cer_3(self): + ref = 'were wolf' + hyp = 'were wolf' + char_error_rate = error_rate.cer(ref, hyp) + self.assertTrue(abs(char_error_rate - 0.0) < 1e-6) + + def test_cer_4(self): ref = 'werewolf' char_error_rate = error_rate.cer(ref, ref) self.assertEqual(char_error_rate, 0.0) - def test_cer_4(self): + def test_cer_5(self): ref = u'我是中国人' hyp = u'我是 美洲人' char_error_rate = error_rate.cer(ref, hyp) self.assertTrue(abs(char_error_rate - 0.6) < 1e-6) - def test_cer_5(self): + def test_cer_6(self): ref = u'我 是 中 国 人' hyp = u'我 是 美 洲 人' char_error_rate = error_rate.cer(ref, hyp, remove_space=True) self.assertTrue(abs(char_error_rate - 0.4) < 1e-6) - def test_cer_6(self): + def test_cer_7(self): ref = u'我是中国人' char_error_rate = error_rate.cer(ref, ref) self.assertFalse(char_error_rate, 0.0) - def test_cer_7(self): + def test_cer_8(self): ref = '' hyp = 'Hypothesis' with self.assertRaises(ValueError):