From c6363c89f956c791e720b3c14d145bcac319e1ee Mon Sep 17 00:00:00 2001
From: Martin <maarand@teklia.com>
Date: Fri, 23 Oct 2020 17:50:37 +0200
Subject: [PATCH] --dataset_name is not required for --split_only
---
kaldi_data_generator.py | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/kaldi_data_generator.py b/kaldi_data_generator.py
index 98f7420..01f5e2f 100644
--- a/kaldi_data_generator.py
+++ b/kaldi_data_generator.py
@@ -288,7 +288,7 @@ def create_parser():
parser = argparse.ArgumentParser(
description="Script to generate Kaldi training data from annotations from Arkindex",
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
- parser.add_argument('-n', '--dataset_name', type=str, required=True,
+ parser.add_argument('-n', '--dataset_name', type=str,
help='Name of the dataset being created for kaldi '
'(useful for distinguishing different datasets when in Lines or Transcriptions directory)')
parser.add_argument('-o', '--out_dir', type=str, required=True,
@@ -337,7 +337,11 @@ def create_parser():
def main():
- args = create_parser().parse_args()
+ parser = create_parser()
+ args = parser.parse_args()
+
+ if not args.dataset_name and not args.split_only:
+ parser.error("--dataset_name must be specified (unless --split-only)")
logger.info(f"ARGS {args} \n")
--
GitLab