Add en_normalization and fix LangSegmenter (#2062)

2025-02-17 18:41:30 +08:00
parent c70daefea2
commit c17dd642c7
5 changed files with 301 additions and 41 deletions
--- a/GPT_SoVITS/TTS_infer_pack/text_segmentation_method.py
+++ b/GPT_SoVITS/TTS_infer_pack/text_segmentation_method.py
@@ -135,7 +135,7 @@ def cut3(inp):
@register_method("cut4")
 def cut4(inp):
    inp = inp.strip("\n")
-    opts = ["%s" % item for item in inp.strip(".").split(".")]
+    opts = re.split(r'(?<!\d)\.(?!\d)', inp.strip("."))
    opts = [item for item in opts if not set(item).issubset(punctuation)]
    return "\n".join(opts)