Update gui.py

gui.py

@@ -1,14 +1,14 @@
 """
-0416后的更新：
-    引入config中half
-    重建npy而不用填写
-    v2支持
-    无f0模型支持
-    修复
-
-    int16：
-    增加无索引支持
-    f0算法改harvest(怎么看就只有这个会影响CPU占用)，但是不这么改效果不好
+Updates after 0416:
+    Import half in config
+    Rebuild npy without filling
+    v2 support
+    No f0 model support
+    Fix
+
+int16：
+    Added support for no index
+    Changed f0 algorithm to harvest (seems like this is the only thing that affects CPU usage), but the effect is not good without this change
 """
 import os, sys, traceback, re
 
@@ -49,7 +49,7 @@ class RVC:
         self, key, f0_method, hubert_path, pth_path, index_path, npy_path, index_rate
     ) -> None:
         """
-        初始化
+        initialization
         """
         try:
             self.f0_up_key = key
@@ -172,7 +172,7 @@ class RVC:
         # Calculate f0_course and f0_bak here
         f0 *= pow(2, f0_up_key / 12)
         # with open("test.txt","w")as f:f.write("\n".join([str(i)for i in f0.tolist()]))
-        tf0 = self.sr // self.window  # 每秒f0点数
+        tf0 = self.sr // self.window  # f0 points per second
         if inp_f0 is not None:
             delta_t = np.round(
                 (inp_f0[:, 0].max() - inp_f0[:, 0].min()) * tf0 + 1
@@ -195,7 +195,7 @@ class RVC:
 
     def infer(self, feats: torch.Tensor) -> np.ndarray:
         """
-        推理函数
+        inference function
         """
         audio = feats.clone().cpu().numpy()
         assert feats.dim() == 1, feats.dim()
@@ -217,7 +217,7 @@ class RVC:
                 self.model.final_proj(logits[0]) if self.version == "v1" else logits[0]
             )
 
-        ####索引优化
+        ####Index optimization
         try:
             if (
                 hasattr(self, "index")
@@ -245,10 +245,10 @@ class RVC:
         print(feats.shape)
         if self.if_f0 == 1:
             pitch, pitchf = self.get_f0(audio, self.f0_up_key)
-            p_len = min(feats.shape[1], 13000, pitch.shape[0])  # 太大了爆显存
+            p_len = min(feats.shape[1], 13000, pitch.shape[0])  # Too big to burst video memory
         else:
             pitch, pitchf = None, None
-            p_len = min(feats.shape[1], 13000)  # 太大了爆显存
+            p_len = min(feats.shape[1], 13000)  # Too big to burst video memory
         torch.cuda.synchronize()
         # print(feats.shape,pitch.shape)
         feats = feats[:, :p_len, :]
@@ -338,7 +338,7 @@ class GUI:
                     ]
                 ),
                 sg.Frame(
-                    title=i18n("加载模型"),
+                    title=i18n("Load model"),
                     layout=[
                         [
                             sg.Input(
@@ -347,7 +347,7 @@ class GUI:
                                 disabled=True,
                             ),
                             sg.FileBrowse(
-                                i18n("Hubert模型"),
+                                i18n("Hubert model"),
                                 initial_folder=os.path.join(os.getcwd()),
                                 file_types=((". pt"),),
                             ),
@@ -358,7 +358,7 @@ class GUI:
                                 key="pth_path",
                             ),
                             sg.FileBrowse(
-                                i18n("选择.pth文件"),
+                                i18n("Select .pth file"),
                                 initial_folder=os.path.join(os.getcwd(), "weights"),
                                 file_types=((". pth"),),
                             ),
@@ -369,19 +369,19 @@ class GUI:
                                 key="index_path",
                             ),
                             sg.FileBrowse(
-                                i18n("选择.index文件"),
+                                i18n("Select .index file"),
                                 initial_folder=os.path.join(os.getcwd(), "logs"),
                                 file_types=((". index"),),
                             ),
                         ],
                         [
                             sg.Input(
-                                default_text="你不需要填写这个You don't need write this.",
+                                default_text="You don't need to write this.",
                                 key="npy_path",
                                 disabled=True,
                             ),
                             sg.FileBrowse(
-                                i18n("选择.npy文件"),
+                                i18n("Select .npy file"),
                                 initial_folder=os.path.join(os.getcwd(), "logs"),
                                 file_types=((". npy"),),
                             ),
@@ -406,7 +406,7 @@ class GUI:
                 sg.Frame(
                     layout=[
                         [
-                            sg.Text(i18n("输入设备")),
+                            sg.Text(i18n("input device")),
                             sg.Combo(
                                 input_devices,
                                 key="sg_input_device",
@@ -414,7 +414,7 @@ class GUI:
                             ),
                         ],
                         [
-                            sg.Text(i18n("输出设备")),
+                            sg.Text(i18n("output device")),
                             sg.Combo(
                                 output_devices,
                                 key="sg_output_device",
@@ -422,14 +422,14 @@ class GUI:
                             ),
                         ],
                     ],
-                    title=i18n("音频设备(请使用同种类驱动)"),
+                    title=i18n("Audio device (please use the same type of driver)"),
                 )
             ],
             [
                 sg.Frame(
                     layout=[
                         [
-                            sg.Text(i18n("响应阈值")),
+                            sg.Text(i18n("response threshold")),
                             sg.Slider(
                                 range=(-60, 0),
                                 key="threhold",
@@ -439,7 +439,7 @@ class GUI:
                             ),
                         ],
                         [
-                            sg.Text(i18n("音调设置")),
+                            sg.Text(i18n("Tone settings")),
                             sg.Slider(
                                 range=(-24, 24),
                                 key="pitch",
@@ -459,12 +459,12 @@ class GUI:
                             ),
                         ],
                     ],
-                    title=i18n("常规设置"),
+                    title=i18n("General settings"),
                 ),
                 sg.Frame(
                     layout=[
                         [
-                            sg.Text(i18n("采样长度")),
+                            sg.Text(i18n("Sample length")),
                             sg.Slider(
                                 range=(0.1, 3.0),
                                 key="block_time",
@@ -474,7 +474,7 @@ class GUI:
                             ),
                         ],
                         [
-                            sg.Text(i18n("淡入淡出长度")),
+                            sg.Text(i18n("Fade Length")),
                             sg.Slider(
                                 range=(0.01, 0.15),
                                 key="crossfade_length",
@@ -484,7 +484,7 @@ class GUI:
                             ),
                         ],
                         [
-                            sg.Text(i18n("额外推理时长")),
+                            sg.Text(i18n("Additional reasoning time")),
                             sg.Slider(
                                 range=(0.05, 3.00),
                                 key="extra_time",
@@ -494,17 +494,17 @@ class GUI:
                             ),
                         ],
                         [
-                            sg.Checkbox(i18n("输入降噪"), key="I_noise_reduce"),
-                            sg.Checkbox(i18n("输出降噪"), key="O_noise_reduce"),
+                            sg.Checkbox(i18n("Input noise reduction"), key="I_noise_reduce"),
+                            sg.Checkbox(i18n("Output noise reduction"), key="O_noise_reduce"),
                         ],
                     ],
-                    title=i18n("性能设置"),
+                    title=i18n("Performance settings"),
                 ),
             ],
             [
-                sg.Button(i18n("开始音频转换"), key="start_vc"),
-                sg.Button(i18n("停止音频转换"), key="stop_vc"),
-                sg.Text(i18n("推理时间(ms):")),
+                sg.Button(i18n("Start audio conversion"), key="start_vc"),
+                sg.Button(i18n("Stop audio conversion"), key="stop_vc"),
+                sg.Text(i18n("Inference time (ms):")),
                 sg.Text("0", key="infer_time"),
             ],
         ]
@@ -557,20 +557,20 @@ class GUI:
 
     def set_values(self, values):
         if len(values["pth_path"].strip()) == 0:
-            sg.popup(i18n("请选择pth文件"))
+            sg.popup(i18n("Please select pth file"))
             return False
         if len(values["index_path"].strip()) == 0:
-            sg.popup(i18n("请选择index文件"))
+            sg.popup(i18n("Please select index file"))
             return False
         pattern = re.compile("[^\x00-\x7F]+")
         if pattern.findall(values["hubert_path"]):
-            sg.popup(i18n("hubert模型路径不可包含中文"))
+            sg.popup(i18n("The hubert model path cannot contain Chinese characters"))
             return False
         if pattern.findall(values["pth_path"]):
-            sg.popup(i18n("pth文件路径不可包含中文"))
+            sg.popup(i18n("pth file path cannot contain Chinese characters"))
             return False
         if pattern.findall(values["index_path"]):
-            sg.popup(i18n("index文件路径不可包含中文"))
+            sg.popup(i18n("The index file path cannot contain Chinese characters"))
             return False
         self.set_devices(values["sg_input_device"], values["sg_output_device"])
         self.config.hubert_path = os.path.join(current_dir, "hubert_base.pt")
@@ -594,7 +594,7 @@ class GUI:
         self.block_frame = int(self.config.block_time * self.config.samplerate)
         self.crossfade_frame = int(self.config.crossfade_time * self.config.samplerate)
         self.sola_search_frame = int(0.012 * self.config.samplerate)
-        self.delay_frame = int(0.01 * self.config.samplerate)  # 往前预留0.02s
+        self.delay_frame = int(0.01 * self.config.samplerate)  # Reserve 0.02s forward
         self.extra_frame = int(self.config.extra_time * self.config.samplerate)
         self.rvc = None
         self.rvc = RVC(
@@ -636,7 +636,7 @@ class GUI:
 
     def soundinput(self):
         """
-        接受音频输入
+        accept audio input
         """
         with sd.Stream(
             callback=self.audio_callback,
@@ -653,7 +653,7 @@ class GUI:
         self, indata: np.ndarray, outdata: np.ndarray, frames, times, status
     ):
         """
-        音频处理
+        audio processing
         """
         start_time = time.perf_counter()
         indata = librosa.to_mono(indata.T)
@@ -733,7 +733,7 @@ class GUI:
         print("f0_method: " + str(self.config.f0_method))
 
     def get_devices(self, update: bool = True):
-        """获取设备列表"""
+        """Get device list"""
         if update:
             sd._terminate()
             sd._initialize()
@@ -770,7 +770,7 @@ class GUI:
         )
 
     def set_devices(self, input_device, output_device):
-        """设置输出设备"""
+        """Set up output device"""
         (
             input_devices,
             output_devices,