From 008ed81052097b85853da62e8e0dbdd4b1b05327 Mon Sep 17 00:00:00 2001
From: Jeronymous <jeromelouradour@gmail.com>
Date: Wed, 17 May 2023 09:01:48 +0200
Subject: [PATCH] glue apostrophes

---
 punctuation/recasepunc.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/punctuation/recasepunc.py b/punctuation/recasepunc.py
index 480f139..4865c05 100644
--- a/punctuation/recasepunc.py
+++ b/punctuation/recasepunc.py
@@ -3,11 +3,10 @@
 """recasepunc file."""
 
 import argparse
-import collections
 import os
 import random
 import sys
-import unicodedata
+import re
 
 import numpy as np
 import torch
@@ -201,6 +200,8 @@ def generate_predictions(config, line):
                     output += cased_token + punctuation_syms[punc_label]
     if previous_label == 0:
         output += '.'
+    # Glue apostrophes back to words
+    output = re.sub(r"(\w) *' *(\w)", r"\1'\2", output)
     return output
 
 mapped_punctuation = {