update

app_local.py

@@ -88,9 +88,9 @@ def infer(ref_audio_orig, ref_text, gen_text, exp_name, remove_silence):
         aseg = AudioSegment.from_file(ref_audio_orig)
         aseg = aseg.set_channels(1)
         audio_duration = len(aseg)
-#        if audio_duration > 15000:
-#            gr.Warning("Audio is over 15s, clipping to only first 15s.")
-#            aseg = aseg[:15000]
+        if audio_duration > 15000:
+            gr.Warning("Audio is over 15s, clipping to only first 15s.")
+            aseg = aseg[:15000]
         aseg.export(f.name, format="wav")
         ref_audio = f.name
     if exp_name == "F5-TTS":

model/utils.py

@@ -134,7 +134,7 @@ def get_tokenizer(dataset_name, tokenizer: str = "pinyin"):
                 - if use "byte", set to 256 (unicode byte range) 
     ''' 
     if tokenizer in ["pinyin", "char"]:
-        with open (f"data/{dataset_name}_{tokenizer}/vocab.txt", "r") as f:
+        with open (f"data/{dataset_name}_{tokenizer}/vocab.txt", "r", encoding="utf-8") as f:
             vocab_char_map = {}
             for i, char in enumerate(f):
                 vocab_char_map[char[:-1]] = i