fix

style_bert_vits2/nlp/japanese/user_dict/word_model.py

@@ -9,7 +9,13 @@ from enum import Enum
 from re import findall, fullmatch
 from typing import List, Optional
 
-from pydantic import BaseModel, Field, validator
+from pydantic import (
+    BaseModel,
+    ConfigDict,
+    Field,
+    ValidationInfo,
+    field_validator,
+)
 
 
 USER_DICT_MIN_PRIORITY = 0
@@ -39,11 +45,11 @@ class UserDictWord(BaseModel):
     mora_count: Optional[int] = Field(title="モーラ数", default=None)
     accent_associative_rule: str = Field(title="アクセント結合規則")
 
-    class Config:
-        validate_assignment = True
+    model_config = ConfigDict(validate_assignment=True, validate_default=True)
 
-    @validator("surface")
-    def convert_to_zenkaku(cls, surface):
+    @field_validator("surface")
+    @classmethod
+    def convert_to_zenkaku(cls, surface: str) -> str:
         return surface.translate(
             str.maketrans(
                 "".join(chr(0x21 + i) for i in range(94)),
@@ -51,8 +57,9 @@ class UserDictWord(BaseModel):
             )
         )
 
-    @validator("pronunciation", pre=True)
-    def check_is_katakana(cls, pronunciation):
+    @field_validator("pronunciation", mode="before")
+    @classmethod
+    def check_is_katakana(cls, pronunciation: str) -> str:
         if not fullmatch(r"[ァ-ヴー]+", pronunciation):
             raise ValueError("発音は有効なカタカナでなくてはいけません。")
         sutegana = ["ァ", "ィ", "ゥ", "ェ", "ォ", "ャ", "ュ", "ョ", "ヮ", "ッ"]
@@ -75,9 +82,12 @@ class UserDictWord(BaseModel):
                     )
         return pronunciation
 
-    @validator("mora_count", pre=True, always=True)
-    def check_mora_count_and_accent_type(cls, mora_count, values):
-        if "pronunciation" not in values or "accent_type" not in values:
+    @field_validator("mora_count", mode="before")
+    @classmethod
+    def check_mora_count_and_accent_type(
+        cls, mora_count: Optional[int], info: ValidationInfo
+    ) -> Optional[int]:
+        if "pronunciation" not in info.data or "accent_type" not in info.data:
             # 適切な場所でエラーを出すようにする
             return mora_count
 
@@ -91,14 +101,14 @@ class UserDictWord(BaseModel):
             mora_count = len(
                 findall(
                     f"(?:{rule_others}|{rule_line_i}|{rule_line_u}|{rule_one_mora})",
-                    values["pronunciation"],
+                    info.data["pronunciation"],
                 )
             )
 
-        if not 0 <= values["accent_type"] <= mora_count:
+        if not 0 <= info.data["accent_type"] <= mora_count:
             raise ValueError(
                 "誤ったアクセント型です({})。 expect: 0 <= accent_type <= {}".format(
-                    values["accent_type"], mora_count
+                    info.data["accent_type"], mora_count
                 )
             )
         return mora_count