fix: Update common_voice.tsv and test_preprocessors.py to current .tsv format

(common_voice.tsv is the first 6 lines of the dev.tsv)
This commit is contained in:
mueller91
2020-09-21 11:57:38 +02:00
parent 6b0621c794
commit 45b3c3d1b0
2 changed files with 10 additions and 24 deletions
+4 -14
View File
@@ -11,18 +11,8 @@ class TestPreprocessors(unittest.TestCase):
root_path = get_tests_input_path()
meta_file = "common_voice.tsv"
items = common_voice(root_path, meta_file)
assert items[0][0] == "Man sollte den Länderfinanzausgleich durch " \
"einen Bundesliga-Soli ersetzen."
assert items[0][1] == os.path.join(get_tests_input_path(), "clips",
"21fce545b24d9a5af0403b949e95e8dd3"
"c10c4ff3e371f14e4d5b4ebf588670b7c"
"9e618285fc872d94a89ed7f0217d9019f"
"e5de33f1577b49dcd518eacf63c4b.wav")
assert items[0][0] == 'The applicants are invited for coffee and visa is given immediately.'
assert items[0][1] == os.path.join(get_tests_input_path(), "clips", "common_voice_en_20005954.wav")
assert items[-1][0] == "Warum werden da keine strafrechtlichen " \
"Konsequenzen gezogen?"
assert items[-1][1] == os.path.join(get_tests_input_path(), "clips",
"ad2f69e053b0e20e01c82b9821fe5787f1"
"cc8e4b0b97f0e4cab1e9a652c577169c82"
"44fb222281a60ee3081854014113e04c4c"
"a43643100b7c01dab0fac11974.wav")
assert items[-1][0] == "Competition for limited resources has also resulted in some local conflicts."
assert items[-1][1] == os.path.join(get_tests_input_path(), "clips", "common_voice_en_19737074.wav")