Open sniperwrb opened 5 years ago
g2p("我写了一行代码") Out[4]: [('我', 'r', 'wo3', 'wo2', '/I/me/my/', '我'), ('写', 'v', 'xie3', 'xie3', '/to write/', '寫'), ('了', 'u', 'le5', 'le5', '/(modal particle intensifying preceding clause)/(completed action marker)/', '了'), ('一行', 'n', 'yi1 xing2', 'yi4 xing2', '/party/delegation/', '一行'), ('代码', 'n', 'dai4 ma3', 'dai4 ma3', '/code/', '代碼')]
The program (word segmentation) thinks that '一行' is a word as transcribed (which is not what we expect), instead of being a phrase pronouncing "yi4 hang2" and meaning "a line of" (which is correct).
g2p("我写了一行代码") Out[4]: [('我', 'r', 'wo3', 'wo2', '/I/me/my/', '我'), ('写', 'v', 'xie3', 'xie3', '/to write/', '寫'), ('了', 'u', 'le5', 'le5', '/(modal particle intensifying preceding clause)/(completed action marker)/', '了'), ('一行', 'n', 'yi1 xing2', 'yi4 xing2', '/party/delegation/', '一行'), ('代码', 'n', 'dai4 ma3', 'dai4 ma3', '/code/', '代碼')]
The program (word segmentation) thinks that '一行' is a word as transcribed (which is not what we expect), instead of being a phrase pronouncing "yi4 hang2" and meaning "a line of" (which is correct).