Merge pull request #392 from klei22/add_ja2ipa_mecab_flow

Adjust the extract json field to spaced_ipa
ReaLLMASIC · Feb 11, 2025 · 80d85a9 · 80d85a9
2 parents 897a1db + 3706f5f
commit 80d85a9
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/data/commonvoice_ja/get_dataset.sh b/data/commonvoice_ja/get_dataset.sh
@@ -64,7 +64,7 @@ python3 utils/ja2ipa.py  -j "$output_file" "$output_json_with_ipa" --use_mecab
 echo "IPA conversion finished."
 
 output_ipa_txt="ja_ipa.txt"
-python3 utils/extract_json_values.py "$output_json_with_ipa" "sentence_ipa" "$output_ipa_txt" 
+python3 utils/extract_json_values.py "$output_json_with_ipa" "spaced_ipa" "$output_ipa_txt"
 echo "IPA extraction finished."
 
 #TODO(gkielian): see if we can fix the parsing of rows instead of deleting