From f0dd73a4197e2b12ec5a28dc26d1512ea7d93846 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=A4=9A=E7=8E=A9=E5=B9=BB=E7=81=B5qwq?=
 <94176676+HuanLinOTO@users.noreply.github.com>
Date: Sun, 9 Jun 2024 00:05:12 +0800
Subject: [PATCH] feat: fallback to system encoding when fail to read file with
 utf-8

---
 infer/lib/train/utils.py | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/infer/lib/train/utils.py b/infer/lib/train/utils.py
index e7bb783..765c54c 100644
--- a/infer/lib/train/utils.py
+++ b/infer/lib/train/utils.py
@@ -278,8 +278,13 @@ def load_wav_to_torch(full_path):
 
 
 def load_filepaths_and_text(filename, split="|"):
-    with open(filename, encoding="utf-8") as f:
-        filepaths_and_text = [line.strip().split(split) for line in f]
+    try:
+        with open(filename, encoding="utf-8") as f:
+            filepaths_and_text = [line.strip().split(split) for line in f]
+    except UnicodeDecodeError:
+        with open(filename) as f:
+            filepaths_and_text = [line.strip().split(split) for line in f]
+    
     return filepaths_and_text