diff --git a/infer/modules/uvr5/mdxnet.py b/infer/modules/uvr5/mdxnet.py
index e6ed653..c6d0e25 100644
--- a/infer/modules/uvr5/mdxnet.py
+++ b/infer/modules/uvr5/mdxnet.py
@@ -216,16 +216,26 @@ class Predictor:
             path_other = "%s/%s_others.wav" % (others_root, basename)
             sf.write(path_vocal, mix - opt, rate)
             sf.write(path_other, opt, rate)
+            opt_path_vocal=path_vocal[:-4] + ".%s" % format
+            opt_path_other=path_other[:-4] + ".%s" % format
             if os.path.exists(path_vocal):
                 os.system(
                     "ffmpeg -i %s -vn %s -q:a 2 -y"
-                    % (path_vocal, path_vocal[:-4] + ".%s" % format)
+                    % (path_vocal, opt_path_vocal)
                 )
+                if(os.path.exists(opt_path_vocal)):
+                    try:
+                        os.remove(path_vocal)
+                    except:pass
             if os.path.exists(path_other):
                 os.system(
                     "ffmpeg -i %s -vn %s -q:a 2 -y"
-                    % (path_other, path_other[:-4] + ".%s" % format)
+                    % (path_other, opt_path_other)
                 )
+                if(os.path.exists(opt_path_other)):
+                    try:
+                        os.remove(path_other)
+                    except:pass
 
 
 class MDXNetDereverb:
@@ -242,5 +252,5 @@ class MDXNetDereverb:
         self.pred = Predictor(self)
         self.device = device
 
-    def _path_audio_(self, input, vocal_root, others_root, format):
+    def _path_audio_(self, input, vocal_root, others_root, format,is_hp3=False):
         self.pred.prediction(input, vocal_root, others_root, format)
diff --git a/infer/modules/uvr5/modules.py b/infer/modules/uvr5/modules.py
index 566609f..151176c 100644
--- a/infer/modules/uvr5/modules.py
+++ b/infer/modules/uvr5/modules.py
@@ -9,7 +9,7 @@ import torch
 
 from configs.config import Config
 from infer.modules.uvr5.mdxnet import MDXNetDereverb
-from infer.modules.uvr5.preprocess import AudioPre, AudioPreDeEcho
+from infer.modules.uvr5.vr import AudioPre, AudioPreDeEcho
 
 config = Config()
 
@@ -34,8 +34,9 @@ def uvr(model_name, inp_root, save_root_vocal, paths, save_root_ins, agg, format
                     os.getenv("weight_uvr5_root"), model_name + ".pth"
                 ),
                 device=config.device,
-                is_half=config.is_half,
+                is_half=config.is_half
             )
+        is_hp3 = "HP3" in model_name
         if inp_root != "":
             paths = [os.path.join(inp_root, name) for name in os.listdir(inp_root)]
         else:
@@ -52,7 +53,7 @@ def uvr(model_name, inp_root, save_root_vocal, paths, save_root_ins, agg, format
                 ):
                     need_reformat = 0
                     pre_fun._path_audio_(
-                        inp_path, save_root_ins, save_root_vocal, format0
+                        inp_path, save_root_ins, save_root_vocal, format0,is_hp3=is_hp3
                     )
                     done = 1
             except:
diff --git a/infer/modules/uvr5/vr.py b/infer/modules/uvr5/vr.py
index c22b291..acd165a 100644
--- a/infer/modules/uvr5/vr.py
+++ b/infer/modules/uvr5/vr.py
@@ -16,7 +16,7 @@ from infer.lib.uvr5_pack.utils import inference
 
 
 class AudioPre:
-    def __init__(self, agg, model_path, device, is_half, tta=False):
+    def __init__(self, agg, model_path, device, is_half, tta = False):
         self.model_path = model_path
         self.device = device
         self.data = {
@@ -41,7 +41,7 @@ class AudioPre:
         self.mp = mp
         self.model = model
 
-    def _path_audio_(self, music_file, ins_root=None, vocal_root=None, format="flac"):
+    def _path_audio_(self, music_file, ins_root=None, vocal_root=None, format="flac",is_hp3=False):
         if ins_root is None and vocal_root is None:
             return "No save root."
         name = os.path.basename(music_file)
@@ -120,18 +120,20 @@ class AudioPre:
             else:
                 wav_instrument = spec_utils.cmb_spectrogram_to_wave(y_spec_m, self.mp)
             logger.info("%s instruments done" % name)
+            if(is_hp3==True):head="vocal_"
+            else:head="instrument_"
             if format in ["wav", "flac"]:
                 sf.write(
                     os.path.join(
                         ins_root,
-                        "instrument_{}_{}.{}".format(name, self.data["agg"], format),
+                        head+"{}_{}.{}".format(name, self.data["agg"], format),
                     ),
                     (np.array(wav_instrument) * 32768).astype("int16"),
                     self.mp.param["sr"],
                 )  #
             else:
                 path = os.path.join(
-                    ins_root, "instrument_{}_{}.wav".format(name, self.data["agg"])
+                    ins_root, head+"{}_{}.wav".format(name, self.data["agg"])
                 )
                 sf.write(
                     path,
@@ -139,11 +141,18 @@ class AudioPre:
                     self.mp.param["sr"],
                 )
                 if os.path.exists(path):
+                    opt_format_path=path[:-4] + ".%s" % format
                     os.system(
                         "ffmpeg -i %s -vn %s -q:a 2 -y"
-                        % (path, path[:-4] + ".%s" % format)
+                        % (path, opt_format_path)
                     )
+                    if os.path.exists(opt_format_path):
+                        try:
+                            os.remove(path)
+                        except:pass
         if vocal_root is not None:
+            if(is_hp3==True):head="instrument_"
+            else:head="vocal_"
             if self.data["high_end_process"].startswith("mirroring"):
                 input_high_end_ = spec_utils.mirroring(
                     self.data["high_end_process"], v_spec_m, input_high_end, self.mp
@@ -158,14 +167,14 @@ class AudioPre:
                 sf.write(
                     os.path.join(
                         vocal_root,
-                        "vocal_{}_{}.{}".format(name, self.data["agg"], format),
+                        head+"{}_{}.{}".format(name, self.data["agg"], format),
                     ),
                     (np.array(wav_vocals) * 32768).astype("int16"),
                     self.mp.param["sr"],
                 )
             else:
                 path = os.path.join(
-                    vocal_root, "vocal_{}_{}.wav".format(name, self.data["agg"])
+                    vocal_root, head+"{}_{}.wav".format(name, self.data["agg"])
                 )
                 sf.write(
                     path,
@@ -173,14 +182,19 @@ class AudioPre:
                     self.mp.param["sr"],
                 )
                 if os.path.exists(path):
+                    opt_format_path=path[:-4] + ".%s" % format
                     os.system(
                         "ffmpeg -i %s -vn %s -q:a 2 -y"
-                        % (path, path[:-4] + ".%s" % format)
+                        % (path, opt_format_path)
                     )
+                    if os.path.exists(opt_format_path):
+                        try:
+                            os.remove(path)
+                        except:pass
 
 
 class AudioPreDeEcho:
-    def __init__(self, agg, model_path, device, is_half, tta=False):
+    def __init__(self, agg, model_path, device, is_half, tta = False):
         self.model_path = model_path
         self.device = device
         self.data = {
@@ -207,7 +221,7 @@ class AudioPreDeEcho:
         self.model = model
 
     def _path_audio_(
-        self, music_file, vocal_root=None, ins_root=None, format="flac"
+        self, music_file, vocal_root=None, ins_root=None, format="flac",is_hp3=False
     ):  # 3个VR模型vocal和ins是反的
         if ins_root is None and vocal_root is None:
             return "No save root."
@@ -306,10 +320,15 @@ class AudioPreDeEcho:
                     self.mp.param["sr"],
                 )
                 if os.path.exists(path):
+                    opt_format_path=path[:-4] + ".%s" % format
                     os.system(
                         "ffmpeg -i %s -vn %s -q:a 2 -y"
-                        % (path, path[:-4] + ".%s" % format)
+                        % (path, opt_format_path)
                     )
+                    if os.path.exists(opt_format_path):
+                        try:
+                            os.remove(path)
+                        except:pass
         if vocal_root is not None:
             if self.data["high_end_process"].startswith("mirroring"):
                 input_high_end_ = spec_utils.mirroring(
@@ -340,7 +359,12 @@ class AudioPreDeEcho:
                     self.mp.param["sr"],
                 )
                 if os.path.exists(path):
+                    opt_format_path=path[:-4] + ".%s" % format
                     os.system(
                         "ffmpeg -i %s -vn %s -q:a 2 -y"
-                        % (path, path[:-4] + ".%s" % format)
+                        % (path, opt_format_path)
                     )
+                    if os.path.exists(opt_format_path):
+                        try:
+                            os.remove(path)
+                        except:pass