chore(format): run black on dev

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

.gitignore

@@ -21,3 +21,8 @@ rmvpe.pt
 
 # To set a Python version for the project
 .tool-versions
+
+/runtime
+/assets/weights/*
+ffmpeg.*
+ffprobe.*

README.md

@@ -93,9 +93,12 @@ pip install -r requirements-ipex.txt
 ```bash
 curl -sSL https://install.python-poetry.org | python3 -
 ```
-通过poetry安装依赖
+
+通过 Poetry 安装依赖时，python 建议使用 3.7-3.10 版本，其余版本在安装 llvmlite==0.39.0 时会出现冲突
 ```bash
-poetry install
+poetry init -n
+poetry env use "path to your python.exe"
+poetry run pip install -r requirments.txt
 ```
 
 ### MacOS
@@ -133,7 +136,7 @@ sudo apt install ffmpeg
 ```bash
 brew install ffmpeg
 ```
-#### Windwos 用户
+#### Windows 用户
 下载后放置在根目录。
 - 下载[ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe)
 
@@ -174,6 +177,12 @@ sudo usermod -aG video $USERNAME
 ```bash
 python infer-web.py
 ```
+
+若先前使用 Poetry 安装依赖，则可以通过以下方式启动WebUI
+```bash
+poetry run python infer-web.py
+```
+
 ### 使用整合包
 下载并解压`RVC-beta.7z`
 #### Windows 用户

configs/config.json

@@ -1 +1 @@
-{"pth_path": "assets/weights/kikiV1.pth", "index_path": "logs/kikiV1.index", "sg_input_device": "VoiceMeeter Output (VB-Audio Vo (MME)", "sg_output_device": "VoiceMeeter Input (VB-Audio Voi (MME)", "sr_type": "sr_model", "threhold": -60.0, "pitch": 12.0, "rms_mix_rate": 0.5, "index_rate": 0.0, "block_time": 0.2, "crossfade_length": 0.08, "extra_time": 2.00, "n_cpu": 4.0, "use_jit": false, "use_pv": false, "f0method": "fcpe"}
+{"pth_path": "assets/weights/kikiV1.pth", "index_path": "logs/kikiV1.index", "sg_hostapi": "MME", "sg_wasapi_exclusive": false, "sg_input_device": "VoiceMeeter Output (VB-Audio Vo", "sg_output_device": "VoiceMeeter Input (VB-Audio Voi", "sr_type": "sr_device", "threhold": -60.0, "pitch": 12.0, "rms_mix_rate": 0.5, "index_rate": 0.0, "block_time": 0.15, "crossfade_length": 0.08, "extra_time": 2.0, "n_cpu": 4.0, "use_jit": false, "use_pv": false, "f0method": "fcpe"}

gui_v1.py

@@ -125,6 +125,8 @@ if __name__ == "__main__":
             self.index_rate: float = 0.0
             self.n_cpu: int = min(n_cpu, 4)
             self.f0method: str = "fcpe"
+            self.sg_hostapi: str = ""
+            self.wasapi_exclusive: bool = False
             self.sg_input_device: str = ""
             self.sg_output_device: str = ""
 
@@ -134,6 +136,7 @@ if __name__ == "__main__":
             self.config = Config()
             self.function = "vc"
             self.delay_time = 0
+            self.hostapis = None
             self.input_devices = None
             self.output_devices = None
             self.input_devices_indices = None
@@ -153,11 +156,25 @@ if __name__ == "__main__":
                     data["crepe"] = data["f0method"] == "crepe"
                     data["rmvpe"] = data["f0method"] == "rmvpe"
                     data["fcpe"] = data["f0method"] == "fcpe"
-                    if data["sg_input_device"] not in self.input_devices:
+                    if data["sg_hostapi"] in self.hostapis:
+                        self.update_devices(hostapi_name=data["sg_hostapi"])
+                        if (
+                            data["sg_input_device"] not in self.input_devices
+                            or data["sg_output_device"] not in self.output_devices
+                        ):
+                            self.update_devices()
+                            data["sg_hostapi"] = self.hostapis[0]
+                            data["sg_input_device"] = self.input_devices[
+                                self.input_devices_indices.index(sd.default.device[0])
+                            ]
+                            data["sg_output_device"] = self.output_devices[
+                                self.output_devices_indices.index(sd.default.device[1])
+                            ]
+                    else:
+                        data["sg_hostapi"] = self.hostapis[0]
                         data["sg_input_device"] = self.input_devices[
                             self.input_devices_indices.index(sd.default.device[0])
                         ]
-                    if data["sg_output_device"] not in self.output_devices:
                         data["sg_output_device"] = self.output_devices[
                             self.output_devices_indices.index(sd.default.device[1])
                         ]
@@ -166,6 +183,8 @@ if __name__ == "__main__":
                     data = {
                         "pth_path": "",
                         "index_path": "",
+                        "sg_hostapi": self.hostapis[0],
+                        "sg_wasapi_exclusive": False,
                         "sg_input_device": self.input_devices[
                             self.input_devices_indices.index(sd.default.device[0])
                         ],
@@ -233,12 +252,30 @@ if __name__ == "__main__":
                 [
                     sg.Frame(
                         layout=[
+                            [
+                                sg.Text(i18n("设备类型")),
+                                sg.Combo(
+                                    self.hostapis,
+                                    key="sg_hostapi",
+                                    default_value=data.get("sg_hostapi", ""),
+                                    enable_events=True,
+                                    size=(20, 1),
+                                ),
+                                sg.Checkbox(
+                                    i18n("独占 WASAPI 设备"),
+                                    key="sg_wasapi_exclusive",
+                                    default=data.get("sg_wasapi_exclusive", False),
+                                    enable_events=True,
+                                ),
+                            ],
                             [
                                 sg.Text(i18n("输入设备")),
                                 sg.Combo(
                                     self.input_devices,
                                     key="sg_input_device",
                                     default_value=data.get("sg_input_device", ""),
+                                    enable_events=True,
+                                    size=(45, 1),
                                 ),
                             ],
                             [
@@ -247,6 +284,8 @@ if __name__ == "__main__":
                                     self.output_devices,
                                     key="sg_output_device",
                                     default_value=data.get("sg_output_device", ""),
+                                    enable_events=True,
+                                    size=(45, 1),
                                 ),
                             ],
                             [
@@ -269,7 +308,7 @@ if __name__ == "__main__":
                                 sg.Text("", key="sr_stream"),
                             ],
                         ],
-                        title=i18n("音频设备(请使用同种类驱动)"),
+                        title=i18n("音频设备"),
                     )
                 ],
                 [
@@ -365,7 +404,7 @@ if __name__ == "__main__":
                             [
                                 sg.Text(i18n("采样长度")),
                                 sg.Slider(
-                                    range=(0.02, 2.4),
+                                    range=(0.02, 1.5),
                                     key="block_time",
                                     resolution=0.01,
                                     orientation="h",
@@ -481,8 +520,13 @@ if __name__ == "__main__":
                 if event == sg.WINDOW_CLOSED:
                     self.stop_stream()
                     exit()
-                if event == "reload_devices":
-                    self.update_devices()
+                if event == "reload_devices" or event == "sg_hostapi":
+                    self.gui_config.sg_hostapi = values["sg_hostapi"]
+                    self.update_devices(hostapi_name=values["sg_hostapi"])
+                    if self.gui_config.sg_hostapi not in self.hostapis:
+                        self.gui_config.sg_hostapi = self.hostapis[0]
+                    self.window["sg_hostapi"].Update(values=self.hostapis)
+                    self.window["sg_hostapi"].Update(value=self.gui_config.sg_hostapi)
                     if self.gui_config.sg_input_device not in self.input_devices:
                         self.gui_config.sg_input_device = self.input_devices[0]
                     self.window["sg_input_device"].Update(values=self.input_devices)
@@ -502,6 +546,8 @@ if __name__ == "__main__":
                         settings = {
                             "pth_path": values["pth_path"],
                             "index_path": values["index_path"],
+                            "sg_hostapi": values["sg_hostapi"],
+                            "sg_wasapi_exclusive": values["sg_wasapi_exclusive"],
                             "sg_input_device": values["sg_input_device"],
                             "sg_output_device": values["sg_output_device"],
                             "sr_type": ["sr_model", "sr_device"][
@@ -544,7 +590,9 @@ if __name__ == "__main__":
                         if values["I_noise_reduce"]:
                             self.delay_time += min(values["crossfade_length"], 0.04)
                         self.window["sr_stream"].update(self.gui_config.samplerate)
-                        self.window["delay_time"].update(int(self.delay_time * 1000))
+                        self.window["delay_time"].update(
+                            int(np.round(self.delay_time * 1000))
+                        )
                 # Parameter hot update
                 if event == "threhold":
                     self.gui_config.threhold = values["threhold"]
@@ -566,7 +614,9 @@ if __name__ == "__main__":
                         self.delay_time += (
                             1 if values["I_noise_reduce"] else -1
                         ) * min(values["crossfade_length"], 0.04)
-                        self.window["delay_time"].update(int(self.delay_time * 1000))
+                        self.window["delay_time"].update(
+                            int(np.round(self.delay_time * 1000))
+                        )
                 elif event == "O_noise_reduce":
                     self.gui_config.O_noise_reduce = values["O_noise_reduce"]
                 elif event == "use_pv":
@@ -594,6 +644,8 @@ if __name__ == "__main__":
             self.set_devices(values["sg_input_device"], values["sg_output_device"])
             self.config.use_jit = False  # values["use_jit"]
             # self.device_latency = values["device_latency"]
+            self.gui_config.sg_hostapi = values["sg_hostapi"]
+            self.gui_config.sg_wasapi_exclusive = values["sg_wasapi_exclusive"]
             self.gui_config.sg_input_device = values["sg_input_device"]
             self.gui_config.sg_output_device = values["sg_output_device"]
             self.gui_config.pth_path = values["pth_path"]
@@ -644,6 +696,7 @@ if __name__ == "__main__":
                 if self.gui_config.sr_type == "sr_model"
                 else self.get_device_samplerate()
             )
+            self.gui_config.channels = self.get_device_channels()
             self.zc = self.gui_config.samplerate // 100
             self.block_frame = (
                 int(
@@ -686,19 +739,18 @@ if __name__ == "__main__":
                 device=self.config.device,
                 dtype=torch.float32,
             )
+            self.input_wav_denoise: torch.Tensor = self.input_wav.clone()
             self.input_wav_res: torch.Tensor = torch.zeros(
                 160 * self.input_wav.shape[0] // self.zc,
                 device=self.config.device,
                 dtype=torch.float32,
             )
+            self.rms_buffer: np.ndarray = np.zeros(4 * self.zc, dtype="float32")
             self.sola_buffer: torch.Tensor = torch.zeros(
                 self.sola_buffer_frame, device=self.config.device, dtype=torch.float32
             )
             self.nr_buffer: torch.Tensor = self.sola_buffer.clone()
             self.output_buffer: torch.Tensor = self.input_wav.clone()
-            self.res_buffer: torch.Tensor = torch.zeros(
-                2 * self.zc, device=self.config.device, dtype=torch.float32
-            )
             self.skip_head = self.extra_frame // self.zc
             self.return_length = (
                 self.block_frame + self.sola_buffer_frame + self.sola_search_frame
@@ -740,13 +792,20 @@ if __name__ == "__main__":
             global flag_vc
             if not flag_vc:
                 flag_vc = True
-                channels = 1 if sys.platform == "darwin" else 2
+                if (
+                    "WASAPI" in self.gui_config.sg_hostapi
+                    and self.gui_config.sg_wasapi_exclusive
+                ):
+                    extra_settings = sd.WasapiSettings(exclusive=True)
+                else:
+                    extra_settings = None
                 self.stream = sd.Stream(
-                    channels=channels,
                     callback=self.audio_callback,
                     blocksize=self.block_frame,
                     samplerate=self.gui_config.samplerate,
+                    channels=self.gui_config.channels,
                     dtype="float32",
+                    extra_settings=extra_settings,
                 )
                 self.stream.start()
 
@@ -755,7 +814,7 @@ if __name__ == "__main__":
             if flag_vc:
                 flag_vc = False
                 if self.stream is not None:
-                    self.stream.stop()
+                    self.stream.abort()
                     self.stream.close()
                     self.stream = None
 
@@ -769,48 +828,54 @@ if __name__ == "__main__":
             start_time = time.perf_counter()
             indata = librosa.to_mono(indata.T)
             if self.gui_config.threhold > -60:
+                indata = np.append(self.rms_buffer, indata)
                 rms = librosa.feature.rms(
                     y=indata, frame_length=4 * self.zc, hop_length=self.zc
-                )
+                )[:, 2:]
+                self.rms_buffer[:] = indata[-4 * self.zc :]
+                indata = indata[2 * self.zc - self.zc // 2 :]
                 db_threhold = (
                     librosa.amplitude_to_db(rms, ref=1.0)[0] < self.gui_config.threhold
                 )
                 for i in range(db_threhold.shape[0]):
                     if db_threhold[i]:
                         indata[i * self.zc : (i + 1) * self.zc] = 0
+                indata = indata[self.zc // 2 :]
             self.input_wav[: -self.block_frame] = self.input_wav[
                 self.block_frame :
             ].clone()
-            self.input_wav[-self.block_frame :] = torch.from_numpy(indata).to(
+            self.input_wav[-indata.shape[0] :] = torch.from_numpy(indata).to(
                 self.config.device
             )
             self.input_wav_res[: -self.block_frame_16k] = self.input_wav_res[
                 self.block_frame_16k :
             ].clone()
             # input noise reduction and resampling
-            if self.gui_config.I_noise_reduce and self.function == "vc":
-                input_wav = self.input_wav[
-                    -self.sola_buffer_frame - self.block_frame - 2 * self.zc :
-                ]
+            if self.gui_config.I_noise_reduce:
+                self.input_wav_denoise[: -self.block_frame] = self.input_wav_denoise[
+                    self.block_frame :
+                ].clone()
+                input_wav = self.input_wav[-self.sola_buffer_frame - self.block_frame :]
                 input_wav = self.tg(
                     input_wav.unsqueeze(0), self.input_wav.unsqueeze(0)
-                )[0, 2 * self.zc :]
+                ).squeeze(0)
                 input_wav[: self.sola_buffer_frame] *= self.fade_in_window
                 input_wav[: self.sola_buffer_frame] += (
                     self.nr_buffer * self.fade_out_window
                 )
+                self.input_wav_denoise[-self.block_frame :] = input_wav[
+                    : self.block_frame
+                ]
                 self.nr_buffer[:] = input_wav[self.block_frame :]
-                input_wav = torch.cat(
-                    (self.res_buffer[:], input_wav[: self.block_frame])
-                )
-                self.res_buffer[:] = input_wav[-2 * self.zc :]
                 self.input_wav_res[-self.block_frame_16k - 160 :] = self.resampler(
-                    input_wav
+                    self.input_wav_denoise[-self.block_frame - 2 * self.zc :]
                 )[160:]
             else:
-                self.input_wav_res[-self.block_frame_16k - 160 :] = self.resampler(
-                    self.input_wav[-self.block_frame - 2 * self.zc :]
-                )[160:]
+                self.input_wav_res[
+                    -160 * (indata.shape[0] // self.zc + 1) :
+                ] = self.resampler(self.input_wav[-indata.shape[0] - 2 * self.zc :])[
+                    160:
+                ]
             # infer
             if self.function == "vc":
                 infer_wav = self.rvc.infer(
@@ -822,14 +887,12 @@ if __name__ == "__main__":
                 )
                 if self.resampler2 is not None:
                     infer_wav = self.resampler2(infer_wav)
+            elif self.gui_config.I_noise_reduce:
+                infer_wav = self.input_wav_denoise[self.extra_frame :].clone()
             else:
-                infer_wav = self.input_wav[
-                    -self.crossfade_frame - self.sola_search_frame - self.block_frame :
-                ].clone()
+                infer_wav = self.input_wav[self.extra_frame :].clone()
             # output noise reduction
-            if (self.gui_config.O_noise_reduce and self.function == "vc") or (
-                self.gui_config.I_noise_reduce and self.function == "im"
-            ):
+            if self.gui_config.O_noise_reduce and self.function == "vc":
                 self.output_buffer[: -self.block_frame] = self.output_buffer[
                     self.block_frame :
                 ].clone()
@@ -839,16 +902,14 @@ if __name__ == "__main__":
                 ).squeeze(0)
             # volume envelop mixing
             if self.gui_config.rms_mix_rate < 1 and self.function == "vc":
+                if self.gui_config.I_noise_reduce:
+                    input_wav = self.input_wav_denoise[self.extra_frame :]
+                else:
+                    input_wav = self.input_wav[self.extra_frame :]
                 rms1 = librosa.feature.rms(
-                    y=self.input_wav_res[
-                        160
-                        * self.skip_head : 160
-                        * (self.skip_head + self.return_length)
-                    ]
-                    .cpu()
-                    .numpy(),
-                    frame_length=640,
-                    hop_length=160,
+                    y=input_wav[: infer_wav.shape[0]].cpu().numpy(),
+                    frame_length=4 * self.zc,
+                    hop_length=self.zc,
                 )
                 rms1 = torch.from_numpy(rms1).to(self.config.device)
                 rms1 = F.interpolate(
@@ -907,19 +968,22 @@ if __name__ == "__main__":
             self.sola_buffer[:] = infer_wav[
                 self.block_frame : self.block_frame + self.sola_buffer_frame
             ]
-            if sys.platform == "darwin":
-                outdata[:] = infer_wav[: self.block_frame].cpu().numpy()[:, np.newaxis]
-            else:
             outdata[:] = (
-                    infer_wav[: self.block_frame].repeat(2, 1).t().cpu().numpy()
+                infer_wav[: self.block_frame]
+                .repeat(self.gui_config.channels, 1)
+                .t()
+                .cpu()
+                .numpy()
             )
             total_time = time.perf_counter() - start_time
             if flag_vc:
                 self.window["infer_time"].update(int(total_time * 1000))
             printt("Infer time: %.2f", total_time)
 
-        def update_devices(self):
+        def update_devices(self, hostapi_name=None):
             """获取设备列表"""
+            global flag_vc
+            flag_vc = False
             sd._terminate()
             sd._initialize()
             devices = sd.query_devices()
@@ -927,25 +991,28 @@ if __name__ == "__main__":
             for hostapi in hostapis:
                 for device_idx in hostapi["devices"]:
                     devices[device_idx]["hostapi_name"] = hostapi["name"]
+            self.hostapis = [hostapi["name"] for hostapi in hostapis]
+            if hostapi_name not in self.hostapis:
+                hostapi_name = self.hostapis[0]
             self.input_devices = [
-                f"{d['name']} ({d['hostapi_name']})"
+                d["name"]
                 for d in devices
-                if d["max_input_channels"] > 0
+                if d["max_input_channels"] > 0 and d["hostapi_name"] == hostapi_name
             ]
             self.output_devices = [
-                f"{d['name']} ({d['hostapi_name']})"
+                d["name"]
                 for d in devices
-                if d["max_output_channels"] > 0
+                if d["max_output_channels"] > 0 and d["hostapi_name"] == hostapi_name
             ]
             self.input_devices_indices = [
                 d["index"] if "index" in d else d["name"]
                 for d in devices
-                if d["max_input_channels"] > 0
+                if d["max_input_channels"] > 0 and d["hostapi_name"] == hostapi_name
             ]
             self.output_devices_indices = [
                 d["index"] if "index" in d else d["name"]
                 for d in devices
-                if d["max_output_channels"] > 0
+                if d["max_output_channels"] > 0 and d["hostapi_name"] == hostapi_name
             ]
 
         def set_devices(self, input_device, output_device):
@@ -964,4 +1031,13 @@ if __name__ == "__main__":
                 sd.query_devices(device=sd.default.device[0])["default_samplerate"]
             )
 
+        def get_device_channels(self):
+            max_input_channels = sd.query_devices(device=sd.default.device[0])[
+                "max_input_channels"
+            ]
+            max_output_channels = sd.query_devices(device=sd.default.device[1])[
+                "max_output_channels"
+            ]
+            return min(max_input_channels, max_output_channels, 2)
+
     gui = GUI()

i18n/locale/en_US.json

@@ -90,6 +90,7 @@
     "版本": "Version",
     "特征提取": "Feature extraction",
     "特征检索库文件路径,为空则使用下拉的选择结果": "Path to the feature index file. Leave blank to use the selected result from the dropdown:",
+    "独占 WASAPI 设备": "独占 WASAPI 设备",
     "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "Recommended +12 key for male to female conversion, and -12 key for female to male conversion. If the sound range goes too far and the voice is distorted, you can also adjust it to the appropriate range by yourself.",
     "目标采样率": "Target sample rate:",
     "算法延迟(ms):": "Algorithmic delays(ms):",
@@ -101,6 +102,7 @@
     "训练模型": "Train model",
     "训练特征索引": "Train feature index",
     "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "Training complete. You can check the training logs in the console or the 'train.log' file under the experiment folder.",
+    "设备类型": "设备类型",
     "请指定说话人id": "Please specify the speaker/singer ID:",
     "请选择index文件": "Please choose the .index file",
     "请选择pth文件": "Please choose the .pth file",
@@ -129,7 +131,7 @@
     "采样长度": "Sample length",
     "重载设备列表": "Reload device list",
     "音调设置": "Pitch settings",
-    "音频设备(请使用同种类驱动)": "Audio device (please use the same type of driver)",
+    "音频设备": "Audio device",
     "音高算法": "pitch detection algorithm",
     "额外推理时长": "Extra inference time"
 }

i18n/locale/es_ES.json

@@ -90,6 +90,7 @@
     "版本": "Versión",
     "特征提取": "Extracción de características",
     "特征检索库文件路径,为空则使用下拉的选择结果": "Ruta del archivo de la biblioteca de características, si está vacío, se utilizará el resultado de la selección desplegable",
+    "独占 WASAPI 设备": "独占 WASAPI 设备",
     "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "Tecla +12 recomendada para conversión de voz de hombre a mujer, tecla -12 para conversión de voz de mujer a hombre. Si el rango de tono es demasiado amplio y causa distorsión, ajústelo usted mismo a un rango adecuado.",
     "目标采样率": "Tasa de muestreo objetivo",
     "算法延迟(ms):": "算法延迟(ms):",
@@ -101,6 +102,7 @@
     "训练模型": "Entrenar Modelo",
     "训练特征索引": "Índice de características",
     "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "Entrenamiento finalizado, puede ver el registro de entrenamiento en la consola o en el archivo train.log en la carpeta del experimento",
+    "设备类型": "设备类型",
     "请指定说话人id": "ID del modelo",
     "请选择index文件": "Seleccione el archivo .index",
     "请选择pth文件": "Seleccione el archivo .pth",
@@ -129,7 +131,7 @@
     "采样长度": "Longitud de muestreo",
     "重载设备列表": "Actualizar lista de dispositivos",
     "音调设置": "Ajuste de tono",
-    "音频设备(请使用同种类驱动)": "Dispositivo de audio (utilice el mismo tipo de controlador)",
+    "音频设备": "Dispositivo de audio",
     "音高算法": "Algoritmo de tono",
     "额外推理时长": "Tiempo de inferencia adicional"
 }

i18n/locale/fr_FR.json

@@ -90,6 +90,7 @@
     "版本": "Version",
     "特征提取": "Extraction des caractéristiques",
     "特征检索库文件路径,为空则使用下拉的选择结果": "Chemin d'accès au fichier d'index des caractéristiques. Laisser vide pour utiliser le résultat sélectionné dans la liste déroulante :",
+    "独占 WASAPI 设备": "独占 WASAPI 设备",
     "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "Il est recommandé d'utiliser la clé +12 pour la conversion homme-femme et la clé -12 pour la conversion femme-homme. Si la plage sonore est trop large et que la voix est déformée, vous pouvez également l'ajuster vous-même à la plage appropriée.",
     "目标采样率": "Taux d'échantillonnage cible :",
     "算法延迟(ms):": "Délais algorithmiques (ms):",
@@ -101,6 +102,7 @@
     "训练模型": "Entraîner le modèle",
     "训练特征索引": "Entraîner l'index des caractéristiques",
     "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "Entraînement terminé. Vous pouvez consulter les rapports d'entraînement dans la console ou dans le fichier 'train.log' situé dans le dossier de l'expérience.",
+    "设备类型": "设备类型",
     "请指定说话人id": "Veuillez spécifier l'ID de l'orateur ou du chanteur :",
     "请选择index文件": "Veuillez sélectionner le fichier d'index",
     "请选择pth文件": "Veuillez sélectionner le fichier pth",
@@ -129,7 +131,7 @@
     "采样长度": "Longueur de l'échantillon",
     "重载设备列表": "Recharger la liste des dispositifs",
     "音调设置": "Réglages de la hauteur",
-    "音频设备(请使用同种类驱动)": "Périphérique audio (veuillez utiliser le même type de pilote)",
+    "音频设备": "Périphérique audio",
     "音高算法": "algorithme de détection de la hauteur",
     "额外推理时长": "Temps d'inférence supplémentaire"
 }

i18n/locale/it_IT.json

@@ -90,6 +90,7 @@
     "版本": "Versione",
     "特征提取": "Estrazione delle caratteristiche",
     "特征检索库文件路径,为空则使用下拉的选择结果": "Percorso del file di indice delle caratteristiche. ",
+    "独占 WASAPI 设备": "独占 WASAPI 设备",
     "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "Tonalità +12 consigliata per la conversione da maschio a femmina e tonalità -12 per la conversione da femmina a maschio. ",
     "目标采样率": "Frequenza di campionamento target:",
     "算法延迟(ms):": "算法延迟(ms):",
@@ -101,6 +102,7 @@
     "训练模型": "Addestra modello",
     "训练特征索引": "Addestra indice delle caratteristiche",
     "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "Addestramento completato. ",
+    "设备类型": "设备类型",
     "请指定说话人id": "Si prega di specificare l'ID del locutore/cantante:",
     "请选择index文件": "请选择index文件",
     "请选择pth文件": "请选择pth 文件",
@@ -129,7 +131,7 @@
     "采样长度": "Lunghezza del campione",
     "重载设备列表": "Ricaricare l'elenco dei dispositivi",
     "音调设置": "Impostazioni del tono",
-    "音频设备(请使用同种类驱动)": "Dispositivo audio (utilizzare lo stesso tipo di driver)",
+    "音频设备": "Dispositivo audio",
     "音高算法": "音高算法",
     "额外推理时长": "Tempo di inferenza extra"
 }

i18n/locale/ja_JP.json

@@ -90,6 +90,7 @@
     "版本": "バージョン",
     "特征提取": "特徴抽出",
     "特征检索库文件路径,为空则使用下拉的选择结果": "特徴検索ライブラリへのパス 空の場合はドロップダウンで選択",
+    "独占 WASAPI 设备": "独占 WASAPI 设备",
     "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "男性から女性へは+12キーをお勧めします。女性から男性へは-12キーをお勧めします。音域が広すぎて音質が劣化した場合は、適切な音域に自分で調整してください。",
     "目标采样率": "目標サンプリングレート",
     "算法延迟(ms):": "算法延迟(ms):",
@@ -101,6 +102,7 @@
     "训练模型": "モデルのトレーニング",
     "训练特征索引": "特徴インデックスのトレーニング",
     "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "トレーニング終了時に、トレーニングログやフォルダ内のtrain.logを確認することができます",
+    "设备类型": "设备类型",
     "请指定说话人id": "話者IDを指定してください",
     "请选择index文件": "indexファイルを選択してください",
     "请选择pth文件": "pthファイルを選択してください",
@@ -129,7 +131,7 @@
     "采样长度": "サンプル長",
     "重载设备列表": "デバイスリストをリロードする",
     "音调设置": "音程設定",
-    "音频设备(请使用同种类驱动)": "オーディオデバイス(同じ種類のドライバーを使用してください)",
+    "音频设备": "オーディオデバイス",
     "音高算法": "ピッチアルゴリズム",
     "额外推理时长": "追加推論時間"
 }

i18n/locale/ru_RU.json

@@ -90,6 +90,7 @@
     "版本": "Версия архитектуры модели:",
     "特征提取": "Извлечь черты",
     "特征检索库文件路径,为空则使用下拉的选择结果": "Путь к файлу индекса черт. Оставьте пустым, чтобы использовать выбранный вариант из списка ниже:",
+    "独占 WASAPI 设备": "独占 WASAPI 设备",
     "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "Рекомендуется выбрать +12 для конвертирования мужского голоса в женский и -12 для конвертирования женского в мужской. Если диапазон голоса слишком велик, и голос искажается, можно выбрать значение на свой вкус.",
     "目标采样率": "Частота дискретизации аудио:",
     "算法延迟(ms):": "算法延迟(ms):",
@@ -101,6 +102,7 @@
     "训练模型": "Обучить модель",
     "训练特征索引": "Обучить индекс черт",
     "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "Обучение модели завершено. Журнал обучения можно просмотреть в консоли или в файле 'train.log' в папке с моделью.",
+    "设备类型": "设备类型",
     "请指定说话人id": "Номер говорящего/поющего:",
     "请选择index文件": "Пожалуйста, выберите файл индекса",
     "请选择pth文件": "Пожалуйста, выберите файл pth",
@@ -129,7 +131,7 @@
     "采样长度": "Длина сэмпла",
     "重载设备列表": "Обновить список устройств",
     "音调设置": "Настройка высоты звука",
-    "音频设备(请使用同种类驱动)": "Аудиоустройство (пожалуйста, используйте такой же тип драйвера)",
+    "音频设备": "Аудиоустройство",
     "音高算法": "Алгоритм оценки высоты звука",
     "额外推理时长": "Доп. время переработки"
 }

i18n/locale/tr_TR.json

@@ -90,6 +90,7 @@
     "版本": "Sürüm",
     "特征提取": "Özellik çıkartma",
     "特征检索库文件路径,为空则使用下拉的选择结果": "Özellik indeksi dosyasının yolunu belirtin. Seçilen sonucu kullanmak için boş bırakın veya açılır menüden seçim yapın.",
+    "独占 WASAPI 设备": "独占 WASAPI 设备",
     "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "Erkekten kadına çevirmek için +12 tuş önerilir, kadından erkeğe çevirmek için ise -12 tuş önerilir. Eğer ses aralığı çok fazla genişler ve ses bozulursa, isteğe bağlı olarak uygun aralığa kendiniz de ayarlayabilirsiniz.",
     "目标采样率": "Hedef örnekleme oranı:",
     "算法延迟(ms):": "算法延迟(ms):",
@@ -101,6 +102,7 @@
     "训练模型": "Modeli Eğit",
     "训练特征索引": "Özellik Dizinini Eğit",
     "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "Eğitim tamamlandı. Eğitim günlüklerini konsolda veya deney klasörü altındaki train.log dosyasında kontrol edebilirsiniz.",
+    "设备类型": "设备类型",
     "请指定说话人id": "Lütfen konuşmacı/sanatçı no belirtin:",
     "请选择index文件": "Lütfen .index dosyası seçin",
     "请选择pth文件": "Lütfen .pth dosyası seçin",
@@ -129,7 +131,7 @@
     "采样长度": "Örnekleme uzunluğu",
     "重载设备列表": "Cihaz listesini yeniden yükle",
     "音调设置": "Pitch ayarları",
-    "音频设备(请使用同种类驱动)": "Ses cihazı (aynı tür sürücüyü kullanın)",
+    "音频设备": "Ses cihazı",
     "音高算法": "音高算法",
     "额外推理时长": "Ekstra çıkartma süresi"
 }

i18n/locale/zh_CN.json

@@ -90,6 +90,7 @@
     "版本": "版本",
     "特征提取": "特征提取",
     "特征检索库文件路径,为空则使用下拉的选择结果": "特征检索库文件路径,为空则使用下拉的选择结果",
+    "独占 WASAPI 设备": "独占 WASAPI 设备",
     "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ",
     "目标采样率": "目标采样率",
     "算法延迟(ms):": "算法延迟(ms):",
@@ -101,6 +102,7 @@
     "训练模型": "训练模型",
     "训练特征索引": "训练特征索引",
     "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log",
+    "设备类型": "设备类型",
     "请指定说话人id": "请指定说话人id",
     "请选择index文件": "请选择index文件",
     "请选择pth文件": "请选择pth文件",
@@ -129,7 +131,7 @@
     "采样长度": "采样长度",
     "重载设备列表": "重载设备列表",
     "音调设置": "音调设置",
-    "音频设备(请使用同种类驱动)": "音频设备(请使用同种类驱动)",
+    "音频设备": "音频设备",
     "音高算法": "音高算法",
     "额外推理时长": "额外推理时长"
 }

i18n/locale/zh_HK.json

@@ -90,6 +90,7 @@
     "版本": "版本",
     "特征提取": "特徵提取",
     "特征检索库文件路径,为空则使用下拉的选择结果": "特徵檢索庫檔路徑,為空則使用下拉的選擇結果",
+    "独占 WASAPI 设备": "独占 WASAPI 设备",
     "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "男性轉女性推薦+12key，女性轉男性推薦-12key，如果音域爆炸導致音色失真也可以自己調整到合適音域。",
     "目标采样率": "目標取樣率",
     "算法延迟(ms):": "算法延迟(ms):",
@@ -101,6 +102,7 @@
     "训练模型": "訓練模型",
     "训练特征索引": "訓練特徵索引",
     "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log",
+    "设备类型": "设备类型",
     "请指定说话人id": "請指定說話人id",
     "请选择index文件": "请选择index文件",
     "请选择pth文件": "请选择pth文件",
@@ -129,7 +131,7 @@
     "采样长度": "取樣長度",
     "重载设备列表": "重載設備列表",
     "音调设置": "音調設定",
-    "音频设备(请使用同种类驱动)": "音訊設備 (請使用同種類驅動)",
+    "音频设备": "音訊設備",
     "音高算法": "音高演算法",
     "额外推理时长": "額外推理時長"
 }

i18n/locale/zh_SG.json

@@ -90,6 +90,7 @@
     "版本": "版本",
     "特征提取": "特徵提取",
     "特征检索库文件路径,为空则使用下拉的选择结果": "特徵檢索庫檔路徑,為空則使用下拉的選擇結果",
+    "独占 WASAPI 设备": "独占 WASAPI 设备",
     "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "男性轉女性推薦+12key，女性轉男性推薦-12key，如果音域爆炸導致音色失真也可以自己調整到合適音域。",
     "目标采样率": "目標取樣率",
     "算法延迟(ms):": "算法延迟(ms):",
@@ -101,6 +102,7 @@
     "训练模型": "訓練模型",
     "训练特征索引": "訓練特徵索引",
     "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log",
+    "设备类型": "设备类型",
     "请指定说话人id": "請指定說話人id",
     "请选择index文件": "请选择index文件",
     "请选择pth文件": "请选择pth文件",
@@ -129,7 +131,7 @@
     "采样长度": "取樣長度",
     "重载设备列表": "重載設備列表",
     "音调设置": "音調設定",
-    "音频设备(请使用同种类驱动)": "音訊設備 (請使用同種類驅動)",
+    "音频设备": "音訊設備",
     "音高算法": "音高演算法",
     "额外推理时长": "額外推理時長"
 }

i18n/locale/zh_TW.json

@@ -90,6 +90,7 @@
     "版本": "版本",
     "特征提取": "特徵提取",
     "特征检索库文件路径,为空则使用下拉的选择结果": "特徵檢索庫檔路徑,為空則使用下拉的選擇結果",
+    "独占 WASAPI 设备": "独占 WASAPI 设备",
     "男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ": "男性轉女性推薦+12key，女性轉男性推薦-12key，如果音域爆炸導致音色失真也可以自己調整到合適音域。",
     "目标采样率": "目標取樣率",
     "算法延迟(ms):": "算法延迟(ms):",
@@ -101,6 +102,7 @@
     "训练模型": "訓練模型",
     "训练特征索引": "訓練特徵索引",
     "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log": "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log",
+    "设备类型": "设备类型",
     "请指定说话人id": "請指定說話人id",
     "请选择index文件": "请选择index文件",
     "请选择pth文件": "请选择pth文件",
@@ -129,7 +131,7 @@
     "采样长度": "取樣長度",
     "重载设备列表": "重載設備列表",
     "音调设置": "音調設定",
-    "音频设备(请使用同种类驱动)": "音訊設備 (請使用同種類驅動)",
+    "音频设备": "音訊設備",
     "音高算法": "音高演算法",
     "额外推理时长": "額外推理時長"
 }

infer/modules/train/train.py

@@ -104,10 +104,11 @@ def main():
     os.environ["MASTER_ADDR"] = "localhost"
     os.environ["MASTER_PORT"] = str(randint(20000, 55555))
     children = []
+    logger = utils.get_logger(hps.model_dir)
     for i in range(n_gpus):
         subproc = mp.Process(
             target=run,
-            args=(i, n_gpus, hps),
+            args=(i, n_gpus, hps, logger),
         )
         children.append(subproc)
         subproc.start()
@@ -116,14 +117,10 @@ def main():
         children[i].join()
 
 
-def run(
-    rank,
-    n_gpus,
-    hps,
-):
+def run(rank, n_gpus, hps, logger: logging.Logger):
     global global_step
     if rank == 0:
-        logger = utils.get_logger(hps.model_dir)
+        # logger = utils.get_logger(hps.model_dir)
         logger.info(hps)
         # utils.check_git_hash(hps.model_dir)
         writer = SummaryWriter(log_dir=hps.model_dir)

pyproject.toml

@@ -1,64 +0,0 @@
-[tool.poetry]
-name = "rvc-beta"
-version = "0.1.0"
-description = ""
-authors = ["lj1995"]
-license = "MIT"
-
-[tool.poetry.dependencies]
-python = "^3.8"
-torch = "^2.0.0"
-torchaudio = "^2.0.1"
-Cython = "^0.29.34"
-gradio = "^4.11.0"
-future = "^0.18.3"
-pydub = "^0.25.1"
-soundfile = "^0.12.1"
-ffmpeg-python = "^0.2.0"
-tensorboardX = "^2.6"
-functorch = "^2.0.0"
-fairseq = "^0.12.2"
-faiss-cpu = "^1.7.2"
-Jinja2 = "^3.1.2"
-json5 = "^0.9.11"
-librosa = "0.9.1"
-llvmlite = "0.39.0"
-Markdown = "^3.4.3"
-matplotlib = "^3.7.1"
-matplotlib-inline = "^0.1.6"
-numba = "0.56.4"
-numpy = "1.23.5"
-scipy = "1.9.3"
-praat-parselmouth = "^0.4.3"
-Pillow = "9.3.0"
-pyworld = "^0.3.2"
-resampy = "^0.4.2"
-scikit-learn = "^1.2.2"
-starlette = "^0.27.0"
-tensorboard = "^2.12.1"
-tensorboard-data-server = "^0.7.0"
-tensorboard-plugin-wit = "^1.8.1"
-torchgen = "^0.0.1"
-tqdm = "^4.65.0"
-tornado = "^6.3"
-Werkzeug = "^2.2.3"
-uc-micro-py = "^1.0.1"
-sympy = "^1.11.1"
-tabulate = "^0.9.0"
-PyYAML = "^6.0"
-pyasn1 = "^0.4.8"
-pyasn1-modules = "^0.2.8"
-fsspec = "^2023.3.0"
-absl-py = "^1.4.0"
-audioread = "^3.0.0"
-uvicorn = "^0.21.1"
-colorama = "^0.4.6"
-torchcrepe = "0.0.20"
-python-dotenv = "^1.0.0"
-av = "^10.0.0"
-
-[tool.poetry.dev-dependencies]
-
-[build-system]
-requires = ["poetry-core>=1.0.0"]
-build-backend = "poetry.core.masonry.api"

tools/dlmodels.sh

@@ -1,566 +1,81 @@
-#!/bin/bash
+#!/bin/sh
 
-echo working dir is $(pwd)
-echo downloading requirement aria2 check.
+printf "working dir is %s\n" "$PWD"
+echo "downloading requirement aria2 check."
 
-if command -v aria2c &> /dev/null
+if command -v aria2c > /dev/null 2>&1
 then
-    echo "aria2c command found"
+    echo "aria2 command found"
 else
-    echo failed. please install aria2
-    sleep 5
+    echo "failed. please install aria2"
     exit 1
 fi
 
-d32="f0D32k.pth"
-d40="f0D40k.pth"
-d48="f0D48k.pth"
-g32="f0G32k.pth"
-g40="f0G40k.pth"
-g48="f0G48k.pth"
+echo "dir check start."
 
-d40v2="f0D40k.pth"
-g40v2="f0G40k.pth"
+check_dir() {
+    [ -d "$1" ] && printf "dir %s checked\n" "$1" || \
+    printf "failed. generating dir %s\n" "$1" && mkdir -p "$1"
+}
 
-dld32="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D32k.pth"
-dld40="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D40k.pth"
-dld48="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D48k.pth"
-dlg32="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G32k.pth"
-dlg40="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G40k.pth"
-dlg48="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G48k.pth"
+check_dir "./assets/pretrained"
+check_dir "./assets/pretrained_v2"
+check_dir "./assets/uvr5_weights"
+check_dir "./assets/uvr5_weights/onnx_dereverb_By_FoxJoy"
 
-dld40v2="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D40k.pth"
-dlg40v2="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G40k.pth"
+echo "dir check finished."
 
-hp2_all="HP2_all_vocals.pth"
-hp3_all="HP3_all_vocals.pth"
-hp5_only="HP5_only_main_vocal.pth"
-VR_DeEchoAggressive="VR-DeEchoAggressive.pth"
-VR_DeEchoDeReverb="VR-DeEchoDeReverb.pth"
-VR_DeEchoNormal="VR-DeEchoNormal.pth"
-onnx_dereverb="vocals.onnx"
-rmvpe="rmvpe.pt"
-
-dlhp2_all="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2_all_vocals.pth"
-dlhp3_all="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP3_all_vocals.pth"
-dlhp5_only="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5_only_main_vocal.pth"
-dlVR_DeEchoAggressive="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/VR-DeEchoAggressive.pth"
-dlVR_DeEchoDeReverb="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/VR-DeEchoDeReverb.pth"
-dlVR_DeEchoNormal="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/VR-DeEchoNormal.pth"
-dlonnx_dereverb="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/onnx_dereverb_By_FoxJoy/vocals.onnx"
-dlrmvpe="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt"
-
-hb="hubert_base.pt"
-
-dlhb="https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt"
-
-echo dir check start.
-
-if [ -d "./assets/pretrained" ]; then
-    echo dir ./assets/pretrained checked.
-else
-    echo failed. generating dir ./assets/pretrained.
-    mkdir pretrained
-fi
-
-if [ -d "./assets/pretrained_v2" ]; then
-    echo dir ./assets/pretrained_v2 checked.
-else
-    echo failed. generating dir ./assets/pretrained_v2.
-    mkdir pretrained_v2
-fi
-
-if [ -d "./assets/uvr5_weights" ]; then
-    echo dir ./assets/uvr5_weights checked.
-else
-    echo failed. generating dir ./assets/uvr5_weights.
-    mkdir uvr5_weights
-fi
-
-if [ -d "./assets/uvr5_weights/onnx_dereverb_By_FoxJoy" ]; then
-    echo dir ./assets/uvr5_weights/onnx_dereverb_By_FoxJoy checked.
-else
-    echo failed. generating dir ./assets/uvr5_weights/onnx_dereverb_By_FoxJoy.
-    mkdir uvr5_weights/onnx_dereverb_By_FoxJoy
-fi
-
-echo dir check finished.
-
-echo required files check start.
-
-echo checking D32k.pth
-if [ -f "./assets/pretrained/D32k.pth" ]; then
-    echo D32k.pth in ./assets/pretrained checked.
-else
+echo "required files check start."
+check_file_pretrained() {
+  printf "checking %s\n" "$2"
+  if [ -f "./assets/""$1""/""$2""" ]; then
+      printf "%s in ./assets/%s checked.\n" "$2" "$1" 
+  else
       echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D32k.pth -d ./assets/pretrained -o D32k.pth
-        if [ -f "./assets/pretrained/D32k.pth" ]; then
-            echo download successful.
+      if command -v aria2c > /dev/null 2>&1; then
+          aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/"$1"/"$2" -d ./assets/"$1" -o "$2"
+          [ -f "./assets/""$1""/""$2""" ] && echo "download successful." || echo "please try again!" && exit 1
       else
-            echo please try again!
+          echo "aria2c command not found. Please install aria2c and try again."
           exit 1
       fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
   fi
-fi
+}
 
-echo checking D40k.pth
-if [ -f "./assets/pretrained/D40k.pth" ]; then
-    echo D40k.pth in ./assets/pretrained checked.
-else
+check_file_special() {
+  printf "checking %s\n" "$2"
+  if [ -f "./assets/""$1""/""$2""" ]; then
+      printf "%s in ./assets/%s checked.\n" "$2" "$1" 
+  else
       echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D40k.pth -d ./assets/pretrained -o D40k.pth
-        if [ -f "./assets/pretrained/D40k.pth" ]; then
-            echo download successful.
+      if command -v aria2c > /dev/null 2>&1; then
+          aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/"$2" -d ./assets/"$1" -o "$2"
+          [ -f "./assets/""$1""/""$2""" ] && echo "download successful." || echo "please try again!" && exit 1
       else
-            echo please try again!
+          echo "aria2c command not found. Please install aria2c and try again."
           exit 1
       fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
   fi
-fi
+}
 
-echo checking D40k.pth
-if [ -f "./assets/pretrained_v2/D40k.pth" ]; then
-    echo D40k.pth in ./assets/pretrained_v2 checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D40k.pth -d ./assets/pretrained_v2 -o D40k.pth
-        if [ -f "./assets/pretrained_v2/D40k.pth" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
+check_file_pretrained pretrained D32k.pth
+check_file_pretrained pretrained D40k.pth
+check_file_pretrained pretrained D48k.pth
+check_file_pretrained pretrained G32k.pth
+check_file_pretrained pretrained G40k.pth
+check_file_pretrained pretrained G48k.pth
+check_file_pretrained pretrained_v2 f0D40k.pth
+check_file_pretrained pretrained_v2 f0G40k.pth
+check_file_pretrained pretrained_v2 D40k.pth
+check_file_pretrained pretrained_v2 G40k.pth
+check_file_pretrained uvr5_weights HP2_all_vocals.pth
+check_file_pretrained uvr5_weights HP3_all_vocals.pth
+check_file_pretrained uvr5_weights HP5_only_main_vocal.pth
+check_file_pretrained uvr5_weights VR-DeEchoAggressive.pth
+check_file_pretrained uvr5_weights VR-DeEchoDeReverb.pth
+check_file_pretrained uvr5_weights VR-DeEchoNormal.pth
+check_file_pretrained uvr5_weights "onnx_dereverb_By_FoxJoy/vocals.onnx"
+check_file_special rmvpe rmvpe.pt
+check_file_special hubert hubert_base.pt
 
-echo checking D48k.pth
-if [ -f "./assets/pretrained/D48k.pth" ]; then
-    echo D48k.pth in ./assets/pretrained checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D48k.pth -d ./assets/pretrained -o D48k.pth
-        if [ -f "./assets/pretrained/D48k.pth" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking G32k.pth
-if [ -f "./assets/pretrained/G32k.pth" ]; then
-    echo G32k.pth in ./assets/pretrained checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G32k.pth -d ./assets/pretrained -o G32k.pth
-        if [ -f "./assets/pretrained/G32k.pth" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking G40k.pth
-if [ -f "./assets/pretrained/G40k.pth" ]; then
-    echo G40k.pth in ./assets/pretrained checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G40k.pth -d ./assets/pretrained -o G40k.pth
-        if [ -f "./assets/pretrained/G40k.pth" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking G40k.pth
-if [ -f "./assets/pretrained_v2/G40k.pth" ]; then
-    echo G40k.pth in ./assets/pretrained_v2 checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G40k.pth -d ./assets/pretrained_v2 -o G40k.pth
-        if [ -f "./assets/pretrained_v2/G40k.pth" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking G48k.pth
-if [ -f "./assets/pretrained/G48k.pth" ]; then
-    echo G48k.pth in ./assets/pretrained checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G48k.pth -d ./assets/pretrained -o G48k.pth
-        if [ -f "./assets/pretrained/G48k.pth" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $d32
-if [ -f "./assets/pretrained/$d32" ]; then
-    echo $d32 in ./assets/pretrained checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dld32 -d ./assets/pretrained -o $d32
-        if [ -f "./assets/pretrained/$d32" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $d40
-if [ -f "./assets/pretrained/$d40" ]; then
-    echo $d40 in ./assets/pretrained checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dld40 -d ./assets/pretrained -o $d40
-        if [ -f "./assets/pretrained/$d40" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $d40v2
-if [ -f "./assets/pretrained_v2/$d40v2" ]; then
-    echo $d40v2 in ./assets/pretrained_v2 checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dld40v2 -d ./assets/pretrained_v2 -o $d40v2
-        if [ -f "./assets/pretrained_v2/$d40v2" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $d48
-if [ -f "./assets/pretrained/$d48" ]; then
-    echo $d48 in ./assets/pretrained checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dld48 -d ./assets/pretrained -o $d48
-        if [ -f "./assets/pretrained/$d48" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $g32
-if [ -f "./assets/pretrained/$g32" ]; then
-    echo $g32 in ./assets/pretrained checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dlg32 -d ./assets/pretrained -o $g32
-        if [ -f "./assets/pretrained/$g32" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $g40
-if [ -f "./assets/pretrained/$g40" ]; then
-    echo $g40 in ./assets/pretrained checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dlg40 -d ./assets/pretrained -o $g40
-        if [ -f "./assets/pretrained/$g40" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $g40v2
-if [ -f "./assets/pretrained_v2/$g40v2" ]; then
-    echo $g40v2 in ./assets/pretrained_v2 checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dlg40v2 -d ./assets/pretrained_v2 -o $g40v2
-        if [ -f "./assets/pretrained_v2/$g40v2" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $g48
-if [ -f "./assets/pretrained/$g48" ]; then
-    echo $g48 in ./assets/pretrained checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dlg48 -d ./assets/pretrained -o $g48
-        if [ -f "./assets/pretrained/$g48" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $hp2_all
-if [ -f "./assets/uvr5_weights/$hp2_all" ]; then
-    echo $hp2_all in ./assets/uvr5_weights checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dlhp2_all -d ./assets/uvr5_weights -o $hp2_all
-        if [ -f "./assets/uvr5_weights/$hp2_all" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $hp3_all
-if [ -f "./assets/uvr5_weights/$hp3_all" ]; then
-    echo $hp3_all in ./assets/uvr5_weights checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dlhp3_all -d ./assets/uvr5_weights -o $hp3_all
-        if [ -f "./assets/uvr5_weights/$hp3_all" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $hp5_only
-if [ -f "./assets/uvr5_weights/$hp5_only" ]; then
-    echo $hp5_only in ./assets/uvr5_weights checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dlhp5_only -d ./assets/uvr5_weights -o $hp5_only
-        if [ -f "./assets/uvr5_weights/$hp5_only" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $VR_DeEchoAggressive
-if [ -f "./assets/uvr5_weights/$VR_DeEchoAggressive" ]; then
-    echo $VR_DeEchoAggressive in ./assets/uvr5_weights checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dlVR_DeEchoAggressive -d ./assets/uvr5_weights -o $VR_DeEchoAggressive
-        if [ -f "./assets/uvr5_weights/$VR_DeEchoAggressive" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $VR_DeEchoDeReverb
-if [ -f "./assets/uvr5_weights/$VR_DeEchoDeReverb" ]; then
-    echo $VR_DeEchoDeReverb in ./assets/uvr5_weights checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dlVR_DeEchoDeReverb -d ./assets/uvr5_weights -o $VR_DeEchoDeReverb
-        if [ -f "./assets/uvr5_weights/$VR_DeEchoDeReverb" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $VR_DeEchoNormal
-if [ -f "./assets/uvr5_weights/$VR_DeEchoNormal" ]; then
-    echo $VR_DeEchoNormal in ./assets/uvr5_weights checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dlVR_DeEchoNormal -d ./assets/uvr5_weights -o $VR_DeEchoNormal
-        if [ -f "./assets/uvr5_weights/$VR_DeEchoNormal" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $onnx_dereverb
-if [ -f "./assets/uvr5_weights/onnx_dereverb_By_FoxJoy/$onnx_dereverb" ]; then
-    echo $onnx_dereverb in ./assets/uvr5_weights/onnx_dereverb_By_FoxJoy checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dlonnx_dereverb -d ./assets/uvr5_weights/onnx_dereverb_By_FoxJoy -o $onnx_dereverb
-        if [ -f "./assets/uvr5_weights/onnx_dereverb_By_FoxJoy/$onnx_dereverb" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $rmvpe
-if [ -f "./assets/rmvpe/$rmvpe" ]; then
-    echo $rmvpe in ./assets/rmvpe checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dlrmvpe -d ./assets/rmvpe -o $rmvpe
-        if [ -f "./assets/rmvpe/$rmvpe" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo checking $hb
-if [ -f "./assets/hubert/$hb" ]; then
-    echo $hb in ./assets/hubert/pretrained checked.
-else
-    echo failed. starting download from huggingface.
-    if command -v aria2c &> /dev/null; then
-        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M $dlhb -d ./assets/hubert/ -o $hb
-        if [ -f "./assets/hubert/$hb" ]; then
-            echo download successful.
-        else
-            echo please try again!
-            exit 1
-        fi
-    else
-        echo aria2c command not found. Please install aria2c and try again.
-        exit 1
-    fi
-fi
-
-echo required files check finished.
+echo "required files check finished."

tools/rvc_for_realtime.py

@@ -91,8 +91,12 @@ class RVC:
             self.pth_path: str = pth_path
             self.index_path = index_path
             self.index_rate = index_rate
-            self.cache_pitch: np.ndarray = np.zeros(1024, dtype="int32")
-            self.cache_pitchf = np.zeros(1024, dtype="float32")
+            self.cache_pitch: torch.Tensor = torch.zeros(
+                1024, device=self.device, dtype=torch.long
+            )
+            self.cache_pitchf = torch.zeros(
+                1024, device=self.device, dtype=torch.float32
+            )
 
             if last_rvc is None:
                 models, _, _ = fairseq.checkpoint_utils.load_model_ensemble_and_task(
@@ -199,15 +203,17 @@ class RVC:
         self.index_rate = new_index_rate
 
     def get_f0_post(self, f0):
-        f0bak = f0.copy()
-        f0_mel = 1127 * np.log(1 + f0 / 700)
+        if not torch.is_tensor(f0):
+            f0 = torch.from_numpy(f0)
+        f0 = f0.float().to(self.device).squeeze()
+        f0_mel = 1127 * torch.log(1 + f0 / 700)
         f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - self.f0_mel_min) * 254 / (
             self.f0_mel_max - self.f0_mel_min
         ) + 1
         f0_mel[f0_mel <= 1] = 1
         f0_mel[f0_mel > 255] = 255
-        f0_coarse = np.rint(f0_mel).astype(np.int32)
-        return f0_coarse, f0bak
+        f0_coarse = torch.round(f0_mel).long()
+        return f0_coarse, f0
 
     def get_f0(self, x, f0_up_key, n_cpu, method="harvest"):
         n_cpu = int(n_cpu)
@@ -299,7 +305,6 @@ class RVC:
         pd = torchcrepe.filter.median(pd, 3)
         f0 = torchcrepe.filter.mean(f0, 3)
         f0[pd < 0.1] = 0
-        f0 = f0[0].cpu().numpy()
         f0 *= pow(2, f0_up_key / 12)
         return self.get_f0_post(f0)
 
@@ -335,7 +340,6 @@ class RVC:
             threshold=0.006,
         )
         f0 *= pow(2, f0_up_key / 12)
-        f0 = f0.squeeze().cpu().numpy()
         return self.get_f0_post(f0)
 
     def infer(
@@ -383,6 +387,7 @@ class RVC:
             traceback.print_exc()
             printt("Index search FAILED")
         t3 = ttime()
+        p_len = input_wav.shape[0] // 160
         if self.if_f0 == 1:
             f0_extractor_frame = block_frame_16k + 800
             if f0method == "rmvpe":
@@ -390,25 +395,14 @@ class RVC:
             pitch, pitchf = self.get_f0(
                 input_wav[-f0_extractor_frame:], self.f0_up_key, self.n_cpu, f0method
             )
-            start_frame = block_frame_16k // 160
-            end_frame = len(self.cache_pitch) - (pitch.shape[0] - 4) + start_frame
-            self.cache_pitch[:] = np.append(
-                self.cache_pitch[start_frame:end_frame], pitch[3:-1]
-            )
-            self.cache_pitchf[:] = np.append(
-                self.cache_pitchf[start_frame:end_frame], pitchf[3:-1]
-            )
+            shift = block_frame_16k // 160
+            self.cache_pitch[:-shift] = self.cache_pitch[shift:].clone()
+            self.cache_pitchf[:-shift] = self.cache_pitchf[shift:].clone()
+            self.cache_pitch[4 - pitch.shape[0] :] = pitch[3:-1]
+            self.cache_pitchf[4 - pitch.shape[0] :] = pitchf[3:-1]
+            cache_pitch = self.cache_pitch[None, -p_len:]
+            cache_pitchf = self.cache_pitchf[None, -p_len:]
         t4 = ttime()
-        p_len = input_wav.shape[0] // 160
-        if self.if_f0 == 1:
-            cache_pitch = (
-                torch.LongTensor(self.cache_pitch[-p_len:]).to(self.device).unsqueeze(0)
-            )
-            cache_pitchf = (
-                torch.FloatTensor(self.cache_pitchf[-p_len:])
-                .to(self.device)
-                .unsqueeze(0)
-            )
         feats = F.interpolate(feats.permute(0, 2, 1), scale_factor=2).permute(0, 2, 1)
         feats = feats[:, :p_len, :]
         p_len = torch.LongTensor([p_len]).to(self.device)