Skip to content

Switch to NFC normalisation by default #257

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Switch to NFC normalisation by default #257

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion ocrolib/lstm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -852,12 +852,15 @@ def ctc_align_targets(outputs,targets,threshold=100.0,verbose=0,debug=0,lo=1e-5)
def normalize_nfkc(s):
return unicodedata.normalize('NFKC',s)

def normalize_nfc(s):
return unicodedata.normalize('NFC',s)

def add_training_info(network):
return network

class SeqRecognizer:
"""Perform sequence recognition using BIDILSTM and alignment."""
def __init__(self,ninput,nstates,noutput=-1,codec=None,normalize=normalize_nfkc):
def __init__(self,ninput,nstates,noutput=-1,codec=None,normalize=normalize_nfc):
self.Ni = ninput
if codec: noutput = codec.size()
assert noutput>0
Expand Down
6 changes: 3 additions & 3 deletions ocropus-rtrain
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,7 +134,7 @@ if args.codec!=[]:
print(args.codec)
for fname in ocrolib.glob_all(args.codec):
transcript = ocrolib.read_text(fname)
l = list(lstm.normalize_nfkc(transcript))
l = list(lstm.normalize_nfc(transcript))
charset = charset.union(l)
charset = sorted(list(charset))
charset = [c for c in charset if c>" " and c!="~"]
Expand Down Expand Up @@ -172,7 +172,7 @@ def load_lstm(fname):
if args.clstm:
network = lstm.SeqRecognizer(args.height,args.hiddensize,
codec=codec,
normalize=lstm.normalize_nfkc)
normalize=lstm.normalize_nfc)
import clstm
mylstm = clstm.make_BIDILSTM()
mylstm.init(network.No,args.hiddensize,network.Ni)
Expand All @@ -193,7 +193,7 @@ else:
last_save = None
network = lstm.SeqRecognizer(args.height,args.hiddensize,
codec=codec,
normalize=lstm.normalize_nfkc)
normalize=lstm.normalize_nfc)
if args.clstm:
import clstm
mylstm = clstm.make_BIDILSTM()
Expand Down