🎈 auto fixes by pre-commit hooks

weclone-audio/src/SparkTTS.py

@@ -184,7 +184,8 @@ class SparkTTS:
 
         # Trim the output tokens to remove the input tokens
         generated_ids = [
-            output_ids[len(input_ids) :] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+            output_ids[len(input_ids) :]
+            for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
         ]
 
         # Decode the generated tokens into text
@@ -192,7 +193,9 @@ class SparkTTS:
 
         # Extract semantic token IDs from the generated text
         pred_semantic_ids = (
-            torch.tensor([int(token) for token in re.findall(r"bicodec_semantic_(\d+)", predicts)]).long().unsqueeze(0)
+            torch.tensor([int(token) for token in re.findall(r"bicodec_semantic_(\d+)", predicts)])
+            .long()
+            .unsqueeze(0)
         )
 
         if gender is not None:

weclone-audio/src/get_sample_audio.py

@@ -14,7 +14,9 @@ def main():
         default=os.path.join(os.path.dirname(__file__), "sample.wav"),
         help="Path to save the audio file (default: sample.wav in script directory)",
     )
-    parser.add_argument("--rate", type=int, default=24000, help="Sample rate for audio conversion (default: 24000)")
+    parser.add_argument(
+        "--rate", type=int, default=24000, help="Sample rate for audio conversion (default: 24000)"
+    )
 
     args = parser.parse_args()
 

weclone/cli.py

@@ -203,7 +203,9 @@ def _check_versions():
             logger.warning(
                 f"警告：您的 settings.jsonc 文件版本 ({settings_version}) 与项目建议的配置版本 ({config_guide_version}) 不一致。"
             )
-            logger.warning("这可能导致意外行为或错误。请从 settings.template.json 复制或更新您的 settings.jsonc 文件。")
+            logger.warning(
+                "这可能导致意外行为或错误。请从 settings.template.json 复制或更新您的 settings.jsonc 文件。"
+            )
             # TODO 根据版本号打印更新日志
             logger.warning(f"配置文件更新日志：\n{config_changelog}")
     elif PYPROJECT_PATH.exists():  # 如果文件存在但未读到版本

weclone/data/chat_parsers/wechat_parser.py

@@ -24,7 +24,9 @@ def copy_wechat_image_dat(wechat_data_dir):
 
     data_processor = DataProcessor()
     if not os.path.exists(data_processor.csv_folder) or not os.listdir(data_processor.csv_folder):
-        print(f"错误：目录 '{data_processor.csv_folder}' 不存在或为空，请检查路径并确保其中包含 CSV 聊天数据文件。")
+        print(
+            f"错误：目录 '{data_processor.csv_folder}' 不存在或为空，请检查路径并确保其中包含 CSV 聊天数据文件。"
+        )
         return
 
     csv_files = data_processor.get_csv_files()

weclone/data/qa_generator.py

@@ -90,7 +90,9 @@ class DataProcessor:
 
     def main(self):
         if not os.path.exists(self.csv_folder) or not os.listdir(self.csv_folder):
-            logger.error(f"错误：目录 '{self.csv_folder}' 不存在或为空，请检查路径并确保其中包含 CSV 聊天数据文件。")
+            logger.error(
+                f"错误：目录 '{self.csv_folder}' 不存在或为空，请检查路径并确保其中包含 CSV 聊天数据文件。"
+            )
             return
 
         csv_files = self.get_csv_files()

weclone/eval/cli_demo.py

@@ -13,7 +13,9 @@ def main():
 
     chat_model = ChatModel()
     messages = []
-    print("Welcome to the CLI application, use `clear` to remove the history, use `exit` to exit the application.")
+    print(
+        "Welcome to the CLI application, use `clear` to remove the history, use `exit` to exit the application."
+    )
 
     while True:
         try:

weclone/utils/config.py

@@ -33,7 +33,9 @@ def load_config(arg_type: str):
             dataset_info_path = os.path.join(config["dataset_dir"], "dataset_info.json")
             dataset_info = commentjson.load(open(dataset_info_path, "r", encoding="utf-8"))[config["dataset"]]
             if dataset_info["columns"].get("history") is None:
-                logger.warning(f"{config['dataset']}数据集不包history字段，尝试使用wechat-sft-with-history数据集")
+                logger.warning(
+                    f"{config['dataset']}数据集不包history字段，尝试使用wechat-sft-with-history数据集"
+                )
                 config["dataset"] = "wechat-sft-with-history"
         if "image" in s_config["make_dataset_args"]["include_type"]:
             config["dataset"] = "wechat-mllm-sft"

weclone/utils/length_cdf.py

@@ -57,7 +57,9 @@ def length_cdf(
     )
     tokenizer_module = load_tokenizer(model_args)
     template = get_template_and_fix_tokenizer(tokenizer_module["tokenizer"], data_args)  # type: ignore
-    trainset = get_dataset(template, model_args, data_args, training_args, "sft", **tokenizer_module)["train_dataset"]  # type: ignore
+    trainset = get_dataset(template, model_args, data_args, training_args, "sft", **tokenizer_module)[
+        "train_dataset"
+    ]  # type: ignore
     total_num = len(trainset)  # type: ignore
     length_dict = defaultdict(int)
     for sample in tqdm(trainset["input_ids"], desc="Collecting lengths"):  # type: ignore