From 609120f3da80d9622fc14803b05faf4bf476013a Mon Sep 17 00:00:00 2001
From: Nicolas Panel <nicolas.panel@live.fr>
Date: Sun, 14 Oct 2018 13:48:59 +0200
Subject: [PATCH] [TrainingSpeech importer] stick to data/alphabet.txt

aims to generate english-complatible dataset since no FR alphabet.txt for now
see https://github.com/mozilla/DeepSpeech/pull/1599#issuecomment-426544379 for more info
---
 bin/import_ts.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/bin/import_ts.py b/bin/import_ts.py
index a2d061ca..51d91153 100755
--- a/bin/import_ts.py
+++ b/bin/import_ts.py
@@ -11,6 +11,7 @@ import sys
 sys.path.insert(1, os.path.join(sys.path[0], '..'))
 
 import csv
+import unidecode
 import zipfile
 
 from os import path
@@ -96,7 +97,7 @@ def cleanup_transcript(text):
     text = text.replace('’', "'").replace('\u00A0', ' ')
     text = PUNCTUATIONS_REG.sub(' ', text)
     text = MULTIPLE_SPACES_REG.sub(' ', text)
-    return text.strip().lower()
+    return unidecode.unidecode(text).strip().lower()
 
 
 if __name__ == "__main__":