summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorschneefux <schneefux+commit@schneefux.xyz>2015-02-02 09:56:21 +0100
committerschneefux <schneefux+commit@schneefux.xyz>2015-02-02 09:56:21 +0100
commit8bdf29bceb8d4e389037f9698ecb759edf964879 (patch)
tree52f198eee8f0d523448f0b4d2a4026227063bc2d
parent2521c58282b34c13d6d47cec16569b04a8ac4c64 (diff)
downloadjasper-client-8bdf29bceb8d4e389037f9698ecb759edf964879.tar.gz
jasper-client-8bdf29bceb8d4e389037f9698ecb759edf964879.zip
be more generous with the phonetisaurus regex
-rw-r--r--client/g2p.py4
1 files changed, 2 insertions, 2 deletions
diff --git a/client/g2p.py b/client/g2p.py
index 7b80226..9595dbf 100644
--- a/client/g2p.py
+++ b/client/g2p.py
@@ -12,8 +12,8 @@ import jasperpath
class PhonetisaurusG2P(object):
- PATTERN = re.compile(r'^(?P<word>.+)\t(?P<precision>\d+\.\d+)\t<s> ' +
- r'(?P<pronounciation>.*) </s>', re.MULTILINE)
+ PATTERN = re.compile(r'^(?P<word>.+)\t(?P<precision>\d+\.\d+)\t(?:<s> )?' +
+ r'(?P<pronounciation>.*?)(?: </s>)?$', re.MULTILINE)
@classmethod
def execute(cls, fst_model, input, is_file=False, nbest=None):