Update f5_tts/model/utils.py

f5_tts/model/utils.py

@@ -109,8 +109,7 @@ def get_tokenizer(dataset_name, tokenizer: str = "pinyin"):
                 - if use "byte", set to 256 (unicode byte range)
     """
     if tokenizer in ["pinyin", "char"]:
-        tokenizer_path = str(f'../../vocab.txt')
-
+        tokenizer_path = os.path.join(files("f5_tts").joinpath("../../data"), f"{dataset_name}_{tokenizer}/vocab.txt")
         with open(tokenizer_path, "r", encoding="utf-8") as f:
             vocab_char_map = {}
             for i, char in enumerate(f):
@@ -132,6 +131,7 @@ def get_tokenizer(dataset_name, tokenizer: str = "pinyin"):
     return vocab_char_map, vocab_size
 
 
+
 # convert char to pinyin
 
 jieba.initialize()
@@ -247,4 +247,3 @@ def sample_from_list(float_list, N):
         random_samples = float_tensor[random_indices]
 
     return random_samples
-