fix

bert_gen.py

@@ -55,7 +55,7 @@ def process_line(x: tuple[str, bool]):
     bert_path = wav_path.replace(".WAV", ".wav").replace(".wav", ".bert.pt")
 
     try:
-        bert = torch.load(bert_path)
+        bert = torch.load(bert_path, weights_only=True)
         assert bert.shape[-1] == len(phone)
     except Exception:
         bert = extract_bert_feature(text, word2ph, Languages(language_str), device)

data_utils.py

@@ -129,7 +129,7 @@ class TextAudioSpeakerLoader(torch.utils.data.Dataset):
         if self.use_mel_spec_posterior:
             spec_filename = spec_filename.replace(".spec.pt", ".mel.pt")
         try:
-            spec = torch.load(spec_filename)
+            spec = torch.load(spec_filename, weights_only=True)
         except:
             if self.use_mel_spec_posterior:
                 spec = mel_spectrogram_torch(
@@ -168,7 +168,7 @@ class TextAudioSpeakerLoader(torch.utils.data.Dataset):
             word2ph[0] += 1
         bert_path = wav_path.replace(".wav", ".bert.pt")
         try:
-            bert_ori = torch.load(bert_path)
+            bert_ori = torch.load(bert_path, weights_only=True)
             assert bert_ori.shape[-1] == len(phone)
         except Exception as e:
             logger.warning("Bert load Failed")

style_bert_vits2/models/utils/checkpoints.py

@@ -32,7 +32,9 @@ def load_checkpoint(
     """
 
     assert os.path.isfile(checkpoint_path)
-    checkpoint_dict = torch.load(checkpoint_path, map_location=device)
+    checkpoint_dict = torch.load(
+        checkpoint_path, map_location=device, weights_only=True
+    )
     iteration = checkpoint_dict["iteration"]
     learning_rate = checkpoint_dict["learning_rate"]
     logger.info(

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:
+    model_config = ConfigDict(validate_assignment=True, validate_default=True)
-        validate_assignment = True
 
-    @validator("surface")
+    @field_validator("surface")
-    def convert_to_zenkaku(cls, 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)
+    @field_validator("pronunciation", mode="before")
-    def check_is_katakana(cls, pronunciation):
+    @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)
+    @field_validator("mora_count", mode="before")
-    def check_mora_count_and_accent_type(cls, mora_count, values):
+    @classmethod
-        if "pronunciation" not in values or "accent_type" not in values:
+    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

tests/test_library_compatibility.py

@@ -0,0 +1,58 @@
+from pathlib import Path
+
+import pytest
+import torch
+from pydantic import ValidationError
+
+from style_bert_vits2.models.utils.checkpoints import load_checkpoint, save_checkpoint
+from style_bert_vits2.nlp.japanese.user_dict.word_model import UserDictWord
+
+
+def _user_dict_word(**overrides: object) -> UserDictWord:
+    values = {
+        "surface": "test",
+        "priority": 5,
+        "part_of_speech": "名詞",
+        "part_of_speech_detail_1": "一般",
+        "part_of_speech_detail_2": "*",
+        "part_of_speech_detail_3": "*",
+        "inflectional_type": "*",
+        "inflectional_form": "*",
+        "stem": "*",
+        "yomi": "テスト",
+        "pronunciation": "テスト",
+        "accent_type": 1,
+        "accent_associative_rule": "*",
+    }
+    values.update(overrides)
+    return UserDictWord.model_validate(values)
+
+
+def test_user_dict_word_uses_pydantic_v2_validation() -> None:
+    word = _user_dict_word()
+
+    assert word.surface == "ｔｅｓｔ"
+    assert word.mora_count == 3
+
+    with pytest.raises(ValidationError):
+        _user_dict_word(pronunciation="てすと")
+
+
+def test_checkpoint_round_trip_with_safe_torch_load(tmp_path: Path) -> None:
+    checkpoint_path = tmp_path / "checkpoint.pth"
+    source = torch.nn.Linear(2, 1)
+    optimizer = torch.optim.AdamW(source.parameters())
+    save_checkpoint(source, optimizer, 1e-4, 12, checkpoint_path)
+
+    destination = torch.nn.Linear(2, 1)
+    destination_optimizer = torch.optim.AdamW(destination.parameters())
+    _, _, learning_rate, iteration = load_checkpoint(
+        checkpoint_path, destination, destination_optimizer
+    )
+
+    assert learning_rate == 1e-4
+    assert iteration == 12
+    for source_parameter, destination_parameter in zip(
+        source.parameters(), destination.parameters()
+    ):
+        assert torch.equal(source_parameter, destination_parameter)