From ac9a34a03f19d215c7a3240bddf383034ec6cbb7 Mon Sep 17 00:00:00 2001
From: Sayo <ws11579@gmail.com>
Date: Tue, 6 May 2025 20:24:16 +0800
Subject: [PATCH] [fix] encoding

---
 data_sampler.py                     | 5 +----
 models/lyrics_utils/zh_num2words.py | 2 +-
 pipeline_ace_step.py                | 2 +-
 trainer.py                          | 4 ++--
 4 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/data_sampler.py b/data_sampler.py
index 306fc79..64b1636 100644
--- a/data_sampler.py
+++ b/data_sampler.py
@@ -6,16 +6,13 @@ import random
 DEFAULT_ROOT_DIR = "examples/input_params"
 
 
-
 class DataSampler:
     def __init__(self, root_dir=DEFAULT_ROOT_DIR):
         self.root_dir = root_dir
-        
-        # glob
         self.input_params_files = list(Path(self.root_dir).glob("*.json"))
 
     def load_json(self, file_path):
-        with open(file_path, "r") as f:
+        with open(file_path, "r", encoding="utf-8") as f:
             return json.load(f)
 
     def sample(self):
diff --git a/models/lyrics_utils/zh_num2words.py b/models/lyrics_utils/zh_num2words.py
index 2c6a941..8029b15 100644
--- a/models/lyrics_utils/zh_num2words.py
+++ b/models/lyrics_utils/zh_num2words.py
@@ -1166,7 +1166,7 @@ if __name__ == "__main__":
     )
 
     ndone = 0
-    with open(args.ifile, "r", encoding="utf8") as istream, open(args.ofile, "w+", encoding="utf8") as ostream:
+    with open(args.ifile, "r", encoding="utf-8") as istream, open(args.ofile, "w+", encoding="utf-8") as ostream:
         if args.format == "tsv":
             reader = csv.DictReader(istream, delimiter="\t")
             assert "TEXT" in reader.fieldnames
diff --git a/pipeline_ace_step.py b/pipeline_ace_step.py
index 9f3b671..3efe548 100644
--- a/pipeline_ace_step.py
+++ b/pipeline_ace_step.py
@@ -1172,7 +1172,7 @@ class ACEStepPipeline:
         for output_audio_path in output_paths:
             input_params_json_save_path = output_audio_path.replace(f".{format}", "_input_params.json")
             input_params_json["audio_path"] = output_audio_path
-            with open(input_params_json_save_path, "w") as f:
+            with open(input_params_json_save_path, "w", encoding="utf-8") as f:
                 json.dump(input_params_json, f, indent=4, ensure_ascii=False)
 
         return output_paths + [input_params_json]
diff --git a/trainer.py b/trainer.py
index 6defa7c..2289e77 100644
--- a/trainer.py
+++ b/trainer.py
@@ -74,7 +74,7 @@ class Pipeline(LightningModule):
                 from peft import LoraConfig
             except ImportError:
                 raise ImportError("Please install peft library to use LoRA training")
-            with open(lora_config_path) as f:
+            with open(lora_config_path, encoding="utf-8") as f:
                 lora_config = json.load(f)
             lora_config = LoraConfig(**lora_config)
             transformers.add_adapter(adapter_config=lora_config)
@@ -626,7 +626,7 @@ class Pipeline(LightningModule):
                 os.makedirs(save_dir, exist_ok=True)
             torchaudio.save(f"{save_dir}/target_wav_{key}_{i}.flac", target_wav.float().cpu(), sr)
             torchaudio.save(f"{save_dir}/pred_wav_{key}_{i}.flac", pred_wav.float().cpu(), sr)
-            with open(f"{save_dir}/key_prompt_lyric_{key}_{i}.txt", "w") as f:
+            with open(f"{save_dir}/key_prompt_lyric_{key}_{i}.txt", "w", encoding="utf-8") as f:
                 f.write(key_prompt_lyric)
             i += 1