From 42a8ab37c5902ebd81503906d8207f3e754627ba Mon Sep 17 00:00:00 2001 From: Matthias Gille Levenson Date: Fri, 19 Apr 2024 16:38:56 +0200 Subject: [PATCH] Switch back to full corpus aligmnent --- main.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/main.py b/main.py index ffbb0fa..d5cca91 100644 --- a/main.py +++ b/main.py @@ -223,7 +223,7 @@ def run_alignments(): prefix = args.prefix use_punctuation = args.use_punctuation print(f"Punctuation for tokenization: {use_punctuation}") - MyAligner = Aligner(corpus_size=100, max_align=3, out_dir=out_dir, use_punctuation=use_punctuation, input_dir=input_dir, main_wit=main_wit, prefix=prefix) + MyAligner = Aligner(corpus_size=None, max_align=3, out_dir=out_dir, use_punctuation=use_punctuation, input_dir=input_dir, main_wit=main_wit, prefix=prefix) MyAligner.parallel_align() utils.write_json(f"result_dir/{out_dir}/alignment_dict.json", MyAligner.alignment_dict) align_dict = utils.read_json(f"result_dir/{out_dir}/alignment_dict.json")