experiments
/
STT
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Document Alphabet methods in Python binding as well

This commit is contained in:
Reuben Morais 2020-07-23 13:00:10 +02:00
parent 38f6afdba8
commit eb33fc1719
1 changed files with 19 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
native_client/ctcdecode/__init__.py
View File

@ -48,15 +48,33 @@ class Alphabet(swigwrapper.Alphabet):
raise ValueError('Alphabet initialization failed with error code 0x{:X}'.format(err)) raise ValueError('Alphabet initialization failed with error code 0x{:X}'.format(err))
def CanEncodeSingle(self, input): def CanEncodeSingle(self, input):
'''
Returns true if the single character/output class has a corresponding label
in the alphabet.
'''
return super(Alphabet, self).CanEncodeSingle(input.encode('utf-8')) return super(Alphabet, self).CanEncodeSingle(input.encode('utf-8'))
def CanEncode(self, input): def CanEncode(self, input):
'''
Returns true if the entire string can be encoded into labels in this
alphabet.
'''
return super(Alphabet, self).CanEncode(input.encode('utf-8')) return super(Alphabet, self).CanEncode(input.encode('utf-8'))
def EncodeSingle(self, input): def EncodeSingle(self, input):
'''
Encode a single character/output class into a label. Character must be in
the alphabet, this method will assert that. Use `CanEncodeSingle` to test.
'''
return super(Alphabet, self).EncodeSingle(input.encode('utf-8')) return super(Alphabet, self).EncodeSingle(input.encode('utf-8'))
def Encode(self, input): def Encode(self, input):
'''
Encode a sequence of character/output classes into a sequence of labels.
Characters are assumed to always take a single Unicode codepoint.
Characters must be in the alphabet, this method will assert that. Use
`CanEncode` and `CanEncodeSingle` to test.
'''
# Convert SWIG's UnsignedIntVec to a Python list # Convert SWIG's UnsignedIntVec to a Python list
res = super(Alphabet, self).Encode(input.encode('utf-8')) res = super(Alphabet, self).Encode(input.encode('utf-8'))
return [el for el in res] return [el for el in res]
@ -66,6 +84,7 @@ class Alphabet(swigwrapper.Alphabet):
return res.decode('utf-8') return res.decode('utf-8')
def Decode(self, input): def Decode(self, input):
'''Decode a sequence of labels into a string.'''
res = super(Alphabet, self).Decode(input) res = super(Alphabet, self).Decode(input)
return res.decode('utf-8') return res.decode('utf-8')