From 0719b4aa5eae1f18bfb3e87648bd1acd4abdc0a9 Mon Sep 17 00:00:00 2001
From: liujing04 <129054828+liujing04@users.noreply.github.com>
Date: Sun, 16 Apr 2023 18:56:20 +0800
Subject: [PATCH] Add files via upload

---
 go-realtime-gui.bat                      | 2 ++
 gui.py                                   | 5 ++++-
 infer-web.py                             | 4 +++-
 train_nsf_sim_cache_sid_load_pretrain.py | 5 +++--
 trainset_preprocess_pipeline_print.py    | 3 +++
 vc_infer_pipeline.py                     | 4 +++-
 6 files changed, 18 insertions(+), 5 deletions(-)
 create mode 100644 go-realtime-gui.bat

diff --git a/go-realtime-gui.bat b/go-realtime-gui.bat
new file mode 100644
index 0000000..ed07321
--- /dev/null
+++ b/go-realtime-gui.bat
@@ -0,0 +1,2 @@
+runtime\python.exe gui.py
+pause
diff --git a/gui.py b/gui.py
index 19b8fed..24fcf1e 100644
--- a/gui.py
+++ b/gui.py
@@ -1,3 +1,6 @@
+import os,sys
+now_dir = os.getcwd()
+sys.path.append(now_dir)
 import PySimpleGUI as sg
 import sounddevice as sd
 import noisereduce as nr
@@ -12,7 +15,7 @@ from infer_pack.models import SynthesizerTrnMs256NSFsid, SynthesizerTrnMs256NSFs
 from i18n import I18nAuto
 
 i18n = I18nAuto()
-
+print(i18n.language_map)
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 
diff --git a/infer-web.py b/infer-web.py
index 488dd7f..00d55b2 100644
--- a/infer-web.py
+++ b/infer-web.py
@@ -139,6 +139,8 @@ def vc_single(
         if hubert_model == None:
             load_hubert()
         if_f0 = cpt.get("f0", 1)
+        file_index = file_index.strip(" ").strip('"').strip("\n").strip('"').strip(" ").replace("trained","added")#防止小白写错，自动帮他替换掉
+        file_big_npy = file_big_npy.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
         audio_opt = vc.pipeline(
             hubert_model,
             net_g,
@@ -936,7 +938,7 @@ with gr.Blocks() as app:
                             minimum=0,
                             maximum=1,
                             label="检索特征占比",
-                            value=1,
+                            value=0.6,
                             interactive=True,
                         )
                     f0_file = gr.File(label=i18n("F0曲线文件, 可选, 一行一个音高, 代替默认F0及升降调"))
diff --git a/train_nsf_sim_cache_sid_load_pretrain.py b/train_nsf_sim_cache_sid_load_pretrain.py
index 1735201..fd38dd5 100644
--- a/train_nsf_sim_cache_sid_load_pretrain.py
+++ b/train_nsf_sim_cache_sid_load_pretrain.py
@@ -21,7 +21,7 @@ import torch.distributed as dist
 from torch.nn.parallel import DistributedDataParallel as DDP
 from torch.cuda.amp import autocast, GradScaler
 from infer_pack import commons
-
+from time import sleep
 from time import time as ttime
 from data_utils import (
     TextAudioLoaderMultiNSFsid,
@@ -45,7 +45,7 @@ global_step = 0
 def main():
     # n_gpus = torch.cuda.device_count()
     os.environ["MASTER_ADDR"] = "localhost"
-    os.environ["MASTER_PORT"] = "5555"
+    os.environ["MASTER_PORT"] = "51515"
 
     mp.spawn(
         run,
@@ -676,6 +676,7 @@ def train_and_evaluate(
             "saving final ckpt:%s"
             % (savee(ckpt, hps.sample_rate, hps.if_f0, hps.name, epoch))
         )
+        sleep(1)
         os._exit(2333333)
 
 
diff --git a/trainset_preprocess_pipeline_print.py b/trainset_preprocess_pipeline_print.py
index 68b89d2..5167c82 100644
--- a/trainset_preprocess_pipeline_print.py
+++ b/trainset_preprocess_pipeline_print.py
@@ -1,4 +1,5 @@
 import sys, os, multiprocessing
+from scipy import signal
 
 now_dir = os.getcwd()
 sys.path.append(now_dir)
@@ -38,6 +39,7 @@ class PreProcess:
             max_sil_kept=150,
         )
         self.sr = sr
+        self.bh, self.ah = signal.butter(N=5, Wn=48, btype='high', fs=self.sr)
         self.per = 3.7
         self.overlap = 0.3
         self.tail = self.per + self.overlap
@@ -69,6 +71,7 @@ class PreProcess:
     def pipeline(self, path, idx0):
         try:
             audio = load_audio(path, self.sr)
+            audio = signal.filtfilt(self.bh, self.ah, audio)
             idx1 = 0
             for audio in self.slicer.slice(audio):
                 i = 0
diff --git a/vc_infer_pipeline.py b/vc_infer_pipeline.py
index 0668e41..1fa41d1 100644
--- a/vc_infer_pipeline.py
+++ b/vc_infer_pipeline.py
@@ -4,7 +4,8 @@ import torch.nn.functional as F
 from config import x_pad, x_query, x_center, x_max
 import scipy.signal as signal
 import pyworld, os, traceback, faiss
-
+from scipy import signal
+bh, ah = signal.butter(N=5, Wn=48, btype='high', fs=16000)
 
 class VC(object):
     def __init__(self, tgt_sr, device, is_half):
@@ -189,6 +190,7 @@ class VC(object):
                 index = big_npy = None
         else:
             index = big_npy = None
+        audio = signal.filtfilt(bh, ah, audio)
         audio_pad = np.pad(audio, (self.window // 2, self.window // 2), mode="reflect")
         opt_ts = []
         if audio_pad.shape[0] > self.t_max: