Upload 14 files

.env

@@ -0,0 +1,9 @@
+OPENBLAS_NUM_THREADS = 1
+no_proxy = localhost, 127.0.0.1, ::1
+
+# You can change the location of the model, etc. by changing here
+weight_root = assets/weights
+weight_uvr5_root = assets/uvr5_weights
+index_root = logs
+outside_index_root = assets/indices
+rmvpe_root = assets/rmvpe

.gitignore

@@ -0,0 +1,28 @@
+.DS_Store
+__pycache__
+/TEMP
+*.pyd
+.venv
+/opt
+tools/aria2c/
+tools/flag.txt
+
+# Imported from huggingface.co/lj1995/VoiceConversionWebUI
+/pretrained
+/pretrained_v2
+/uvr5_weights
+hubert_base.pt
+rmvpe.onnx
+rmvpe.pt
+
+# Generated by RVC
+/logs
+/weights
+
+# To set a Python version for the project
+.tool-versions
+
+/runtime
+/assets/weights/*
+ffmpeg.*
+ffprobe.*

config.json

@@ -0,0 +1 @@
+{"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, "formant": 0.0, "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"}

config.py

@@ -0,0 +1,254 @@
+import argparse
+import os
+import sys
+import json
+import shutil
+from multiprocessing import cpu_count
+
+import torch
+
+try:
+    import intel_extension_for_pytorch as ipex  # pylint: disable=import-error, unused-import
+
+    if torch.xpu.is_available():
+        from infer.modules.ipex import ipex_init
+
+        ipex_init()
+except Exception:  # pylint: disable=broad-exception-caught
+    pass
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+version_config_list = [
+    "v1/32k.json",
+    "v1/40k.json",
+    "v1/48k.json",
+    "v2/48k.json",
+    "v2/32k.json",
+]
+
+
+def singleton_variable(func):
+    def wrapper(*args, **kwargs):
+        if not wrapper.instance:
+            wrapper.instance = func(*args, **kwargs)
+        return wrapper.instance
+
+    wrapper.instance = None
+    return wrapper
+
+
+@singleton_variable
+class Config:
+    def __init__(self):
+        self.device = "cuda:0"
+        self.is_half = True
+        self.use_jit = False
+        self.n_cpu = 0
+        self.gpu_name = None
+        self.json_config = self.load_config_json()
+        self.gpu_mem = None
+        (
+            self.python_cmd,
+            self.listen_port,
+            self.iscolab,
+            self.noparallel,
+            self.noautoopen,
+            self.dml,
+        ) = self.arg_parse()
+        self.instead = ""
+        self.preprocess_per = 3.7
+        self.x_pad, self.x_query, self.x_center, self.x_max = self.device_config()
+
+    @staticmethod
+    def load_config_json() -> dict:
+        d = {}
+        for config_file in version_config_list:
+            p = f"configs/inuse/{config_file}"
+            if not os.path.exists(p):
+                shutil.copy(f"configs/{config_file}", p)
+            with open(f"configs/inuse/{config_file}", "r") as f:
+                d[config_file] = json.load(f)
+        return d
+
+    @staticmethod
+    def arg_parse() -> tuple:
+        exe = sys.executable or "python"
+        parser = argparse.ArgumentParser()
+        parser.add_argument("--port", type=int, default=7865, help="Listen port")
+        parser.add_argument("--pycmd", type=str, default=exe, help="Python command")
+        parser.add_argument("--colab", action="store_true", help="Launch in colab")
+        parser.add_argument(
+            "--noparallel", action="store_true", help="Disable parallel processing"
+        )
+        parser.add_argument(
+            "--noautoopen",
+            action="store_true",
+            help="Do not open in browser automatically",
+        )
+        parser.add_argument(
+            "--dml",
+            action="store_true",
+            help="torch_dml",
+        )
+        cmd_opts = parser.parse_args()
+
+        cmd_opts.port = cmd_opts.port if 0 <= cmd_opts.port <= 65535 else 7865
+
+        return (
+            cmd_opts.pycmd,
+            cmd_opts.port,
+            cmd_opts.colab,
+            cmd_opts.noparallel,
+            cmd_opts.noautoopen,
+            cmd_opts.dml,
+        )
+
+    # has_mps is only available in nightly pytorch (for now) and MasOS 12.3+.
+    # check `getattr` and try it for compatibility
+    @staticmethod
+    def has_mps() -> bool:
+        if not torch.backends.mps.is_available():
+            return False
+        try:
+            torch.zeros(1).to(torch.device("mps"))
+            return True
+        except Exception:
+            return False
+
+    @staticmethod
+    def has_xpu() -> bool:
+        if hasattr(torch, "xpu") and torch.xpu.is_available():
+            return True
+        else:
+            return False
+
+    def use_fp32_config(self):
+        for config_file in version_config_list:
+            self.json_config[config_file]["train"]["fp16_run"] = False
+            with open(f"configs/inuse/{config_file}", "r") as f:
+                strr = f.read().replace("true", "false")
+            with open(f"configs/inuse/{config_file}", "w") as f:
+                f.write(strr)
+            logger.info("overwrite " + config_file)
+        self.preprocess_per = 3.0
+        logger.info("overwrite preprocess_per to %d" % (self.preprocess_per))
+
+    def device_config(self) -> tuple:
+        if torch.cuda.is_available():
+            if self.has_xpu():
+                self.device = self.instead = "xpu:0"
+                self.is_half = True
+            i_device = int(self.device.split(":")[-1])
+            self.gpu_name = torch.cuda.get_device_name(i_device)
+            if (
+                ("16" in self.gpu_name and "V100" not in self.gpu_name.upper())
+                or "P40" in self.gpu_name.upper()
+                or "P10" in self.gpu_name.upper()
+                or "1060" in self.gpu_name
+                or "1070" in self.gpu_name
+                or "1080" in self.gpu_name
+            ):
+                logger.info("Found GPU %s, force to fp32", self.gpu_name)
+                self.is_half = False
+                self.use_fp32_config()
+            else:
+                logger.info("Found GPU %s", self.gpu_name)
+            self.gpu_mem = int(
+                torch.cuda.get_device_properties(i_device).total_memory
+                / 1024
+                / 1024
+                / 1024
+                + 0.4
+            )
+            if self.gpu_mem <= 4:
+                self.preprocess_per = 3.0
+        elif self.has_mps():
+            logger.info("No supported Nvidia GPU found")
+            self.device = self.instead = "mps"
+            self.is_half = False
+            self.use_fp32_config()
+        else:
+            logger.info("No supported Nvidia GPU found")
+            self.device = self.instead = "cpu"
+            self.is_half = False
+            self.use_fp32_config()
+
+        if self.n_cpu == 0:
+            self.n_cpu = cpu_count()
+
+        if self.is_half:
+            # 6G显存配置
+            x_pad = 3
+            x_query = 10
+            x_center = 60
+            x_max = 65
+        else:
+            # 5G显存配置
+            x_pad = 1
+            x_query = 6
+            x_center = 38
+            x_max = 41
+
+        if self.gpu_mem is not None and self.gpu_mem <= 4:
+            x_pad = 1
+            x_query = 5
+            x_center = 30
+            x_max = 32
+        if self.dml:
+            logger.info("Use DirectML instead")
+            if (
+                os.path.exists(
+                    "runtime\Lib\site-packages\onnxruntime\capi\DirectML.dll"
+                )
+                == False
+            ):
+                try:
+                    os.rename(
+                        "runtime\Lib\site-packages\onnxruntime",
+                        "runtime\Lib\site-packages\onnxruntime-cuda",
+                    )
+                except:
+                    pass
+                try:
+                    os.rename(
+                        "runtime\Lib\site-packages\onnxruntime-dml",
+                        "runtime\Lib\site-packages\onnxruntime",
+                    )
+                except:
+                    pass
+            # if self.device != "cpu":
+            import torch_directml
+
+            self.device = torch_directml.device(torch_directml.default_device())
+            self.is_half = False
+        else:
+            if self.instead:
+                logger.info(f"Use {self.instead} instead")
+            if (
+                os.path.exists(
+                    "runtime\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"
+                )
+                == False
+            ):
+                try:
+                    os.rename(
+                        "runtime\Lib\site-packages\onnxruntime",
+                        "runtime\Lib\site-packages\onnxruntime-dml",
+                    )
+                except:
+                    pass
+                try:
+                    os.rename(
+                        "runtime\Lib\site-packages\onnxruntime-cuda",
+                        "runtime\Lib\site-packages\onnxruntime",
+                    )
+                except:
+                    pass
+        logger.info(
+            "Half-precision floating-point: %s, device: %s"
+            % (self.is_half, self.device)
+        )
+        return x_pad, x_query, x_center, x_max

download_models.py

@@ -0,0 +1,79 @@
+import os
+from pathlib import Path
+import requests
+
+RVC_DOWNLOAD_LINK = "https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/"
+
+BASE_DIR = Path(__file__).resolve().parent.parent
+
+
+def dl_model(link, model_name, dir_name):
+    with requests.get(f"{link}{model_name}") as r:
+        r.raise_for_status()
+        os.makedirs(os.path.dirname(dir_name / model_name), exist_ok=True)
+        with open(dir_name / model_name, "wb") as f:
+            for chunk in r.iter_content(chunk_size=8192):
+                f.write(chunk)
+
+
+if __name__ == "__main__":
+    print("Downloading hubert_base.pt...")
+    dl_model(RVC_DOWNLOAD_LINK, "hubert_base.pt", BASE_DIR / "assets/hubert")
+    print("Downloading rmvpe.pt...")
+    dl_model(RVC_DOWNLOAD_LINK, "rmvpe.pt", BASE_DIR / "assets/rmvpe")
+    print("Downloading vocals.onnx...")
+    dl_model(
+        RVC_DOWNLOAD_LINK + "uvr5_weights/onnx_dereverb_By_FoxJoy/",
+        "vocals.onnx",
+        BASE_DIR / "assets/uvr5_weights/onnx_dereverb_By_FoxJoy",
+    )
+
+    rvc_models_dir = BASE_DIR / "assets/pretrained"
+
+    print("Downloading pretrained models:")
+
+    model_names = [
+        "D32k.pth",
+        "D40k.pth",
+        "D48k.pth",
+        "G32k.pth",
+        "G40k.pth",
+        "G48k.pth",
+        "f0D32k.pth",
+        "f0D40k.pth",
+        "f0D48k.pth",
+        "f0G32k.pth",
+        "f0G40k.pth",
+        "f0G48k.pth",
+    ]
+    for model in model_names:
+        print(f"Downloading {model}...")
+        dl_model(RVC_DOWNLOAD_LINK + "pretrained/", model, rvc_models_dir)
+
+    rvc_models_dir = BASE_DIR / "assets/pretrained_v2"
+
+    print("Downloading pretrained models v2:")
+
+    for model in model_names:
+        print(f"Downloading {model}...")
+        dl_model(RVC_DOWNLOAD_LINK + "pretrained_v2/", model, rvc_models_dir)
+
+    print("Downloading uvr5_weights:")
+
+    rvc_models_dir = BASE_DIR / "assets/uvr5_weights"
+
+    model_names = [
+        "HP2-%E4%BA%BA%E5%A3%B0vocals%2B%E9%9D%9E%E4%BA%BA%E5%A3%B0instrumentals.pth",
+        "HP2_all_vocals.pth",
+        "HP3_all_vocals.pth",
+        "HP5-%E4%B8%BB%E6%97%8B%E5%BE%8B%E4%BA%BA%E5%A3%B0vocals%2B%E5%85%B6%E4%BB%96instrumentals.pth",
+        "HP5_only_main_vocal.pth",
+        "VR-DeEchoAggressive.pth",
+        "VR-DeEchoDeReverb.pth",
+        "VR-DeEchoNormal.pth",
+    ]
+    for model in model_names:
+        print(f"Downloading {model}...")
+        dl_model(RVC_DOWNLOAD_LINK + "uvr5_weights/", model, rvc_models_dir)
+
+    print("All models downloaded!")

infer-web.py

@@ -0,0 +1,1619 @@
+import os
+import sys
+from dotenv import load_dotenv
+
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+load_dotenv()
+from infer.modules.vc.modules import VC
+from infer.modules.uvr5.modules import uvr
+from infer.lib.train.process_ckpt import (
+    change_info,
+    extract_small_model,
+    merge,
+    show_info,
+)
+from i18n.i18n import I18nAuto
+from configs.config import Config
+from sklearn.cluster import MiniBatchKMeans
+import torch, platform
+import numpy as np
+import gradio as gr
+import faiss
+import fairseq
+import pathlib
+import json
+from time import sleep
+from subprocess import Popen
+from random import shuffle
+import warnings
+import traceback
+import threading
+import shutil
+import logging
+
+
+logging.getLogger("numba").setLevel(logging.WARNING)
+logging.getLogger("httpx").setLevel(logging.WARNING)
+
+logger = logging.getLogger(__name__)
+
+tmp = os.path.join(now_dir, "TEMP")
+shutil.rmtree(tmp, ignore_errors=True)
+shutil.rmtree("%s/runtime/Lib/site-packages/infer_pack" % (now_dir), ignore_errors=True)
+shutil.rmtree("%s/runtime/Lib/site-packages/uvr5_pack" % (now_dir), ignore_errors=True)
+os.makedirs(tmp, exist_ok=True)
+os.makedirs(os.path.join(now_dir, "logs"), exist_ok=True)
+os.makedirs(os.path.join(now_dir, "assets/weights"), exist_ok=True)
+os.environ["TEMP"] = tmp
+warnings.filterwarnings("ignore")
+torch.manual_seed(114514)
+
+
+config = Config()
+vc = VC(config)
+
+
+if config.dml == True:
+
+    def forward_dml(ctx, x, scale):
+        ctx.scale = scale
+        res = x.clone().detach()
+        return res
+
+    fairseq.modules.grad_multiply.GradMultiply.forward = forward_dml
+i18n = I18nAuto()
+logger.info(i18n)
+# 判断是否有能用来训练和加速推理的N卡
+ngpu = torch.cuda.device_count()
+gpu_infos = []
+mem = []
+if_gpu_ok = False
+
+if torch.cuda.is_available() or ngpu != 0:
+    for i in range(ngpu):
+        gpu_name = torch.cuda.get_device_name(i)
+        if any(
+            value in gpu_name.upper()
+            for value in [
+                "10",
+                "16",
+                "20",
+                "30",
+                "40",
+                "A2",
+                "A3",
+                "A4",
+                "P4",
+                "A50",
+                "500",
+                "A60",
+                "70",
+                "80",
+                "90",
+                "M4",
+                "T4",
+                "TITAN",
+                "4060",
+                "L",
+                "6000",
+            ]
+        ):
+            # A10#A100#V100#A40#P40#M40#K80#A4500
+            if_gpu_ok = True  # 至少有一张能用的N卡
+            gpu_infos.append("%s\t%s" % (i, gpu_name))
+            mem.append(
+                int(
+                    torch.cuda.get_device_properties(i).total_memory
+                    / 1024
+                    / 1024
+                    / 1024
+                    + 0.4
+                )
+            )
+if if_gpu_ok and len(gpu_infos) > 0:
+    gpu_info = "\n".join(gpu_infos)
+    default_batch_size = min(mem) // 2
+else:
+    gpu_info = i18n("很遗憾您这没有能用的显卡来支持您训练")
+    default_batch_size = 1
+gpus = "-".join([i[0] for i in gpu_infos])
+
+
+class ToolButton(gr.Button, gr.components.FormComponent):
+    """Small button with single emoji as text, fits inside gradio forms"""
+
+    def __init__(self, **kwargs):
+        super().__init__(variant="tool", **kwargs)
+
+    def get_block_name(self):
+        return "button"
+
+
+weight_root = os.getenv("weight_root")
+weight_uvr5_root = os.getenv("weight_uvr5_root")
+index_root = os.getenv("index_root")
+outside_index_root = os.getenv("outside_index_root")
+
+names = []
+for name in os.listdir(weight_root):
+    if name.endswith(".pth"):
+        names.append(name)
+index_paths = []
+
+
+def lookup_indices(index_root):
+    global index_paths
+    for root, dirs, files in os.walk(index_root, topdown=False):
+        for name in files:
+            if name.endswith(".index") and "trained" not in name:
+                index_paths.append("%s/%s" % (root, name))
+
+
+lookup_indices(index_root)
+lookup_indices(outside_index_root)
+uvr5_names = []
+for name in os.listdir(weight_uvr5_root):
+    if name.endswith(".pth") or "onnx" in name:
+        uvr5_names.append(name.replace(".pth", ""))
+
+
+def change_choices():
+    names = []
+    for name in os.listdir(weight_root):
+        if name.endswith(".pth"):
+            names.append(name)
+    index_paths = []
+    for root, dirs, files in os.walk(index_root, topdown=False):
+        for name in files:
+            if name.endswith(".index") and "trained" not in name:
+                index_paths.append("%s/%s" % (root, name))
+    return {"choices": sorted(names), "__type__": "update"}, {
+        "choices": sorted(index_paths),
+        "__type__": "update",
+    }
+
+
+def clean():
+    return {"value": "", "__type__": "update"}
+
+
+def export_onnx(ModelPath, ExportedPath):
+    from infer.modules.onnx.export import export_onnx as eo
+
+    eo(ModelPath, ExportedPath)
+
+
+sr_dict = {
+    "32k": 32000,
+    "40k": 40000,
+    "48k": 48000,
+}
+
+
+def if_done(done, p):
+    while 1:
+        if p.poll() is None:
+            sleep(0.5)
+        else:
+            break
+    done[0] = True
+
+
+def if_done_multi(done, ps):
+    while 1:
+        # poll==None代表进程未结束
+        # 只要有一个进程未结束都不停
+        flag = 1
+        for p in ps:
+            if p.poll() is None:
+                flag = 0
+                sleep(0.5)
+                break
+        if flag == 1:
+            break
+    done[0] = True
+
+
+def preprocess_dataset(trainset_dir, exp_dir, sr, n_p):
+    sr = sr_dict[sr]
+    os.makedirs("%s/logs/%s" % (now_dir, exp_dir), exist_ok=True)
+    f = open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "w")
+    f.close()
+    cmd = '"%s" infer/modules/train/preprocess.py "%s" %s %s "%s/logs/%s" %s %.1f' % (
+        config.python_cmd,
+        trainset_dir,
+        sr,
+        n_p,
+        now_dir,
+        exp_dir,
+        config.noparallel,
+        config.preprocess_per,
+    )
+    logger.info("Execute: " + cmd)
+    # , stdin=PIPE, stdout=PIPE,stderr=PIPE,cwd=now_dir
+    p = Popen(cmd, shell=True)
+    # 煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+    done = [False]
+    threading.Thread(
+        target=if_done,
+        args=(
+            done,
+            p,
+        ),
+    ).start()
+    while 1:
+        with open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "r") as f:
+            yield (f.read())
+        sleep(1)
+        if done[0]:
+            break
+    with open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "r") as f:
+        log = f.read()
+    logger.info(log)
+    yield log
+
+
+# but2.click(extract_f0,[gpus6,np7,f0method8,if_f0_3,trainset_dir4],[info2])
+def extract_f0_feature(gpus, n_p, f0method, if_f0, exp_dir, version19, gpus_rmvpe):
+    gpus = gpus.split("-")
+    os.makedirs("%s/logs/%s" % (now_dir, exp_dir), exist_ok=True)
+    f = open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "w")
+    f.close()
+    if if_f0:
+        if f0method != "rmvpe_gpu":
+            cmd = (
+                '"%s" infer/modules/train/extract/extract_f0_print.py "%s/logs/%s" %s %s'
+                % (
+                    config.python_cmd,
+                    now_dir,
+                    exp_dir,
+                    n_p,
+                    f0method,
+                )
+            )
+            logger.info("Execute: " + cmd)
+            p = Popen(
+                cmd, shell=True, cwd=now_dir
+            )  # , stdin=PIPE, stdout=PIPE,stderr=PIPE
+            # 煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+            done = [False]
+            threading.Thread(
+                target=if_done,
+                args=(
+                    done,
+                    p,
+                ),
+            ).start()
+        else:
+            if gpus_rmvpe != "-":
+                gpus_rmvpe = gpus_rmvpe.split("-")
+                leng = len(gpus_rmvpe)
+                ps = []
+                for idx, n_g in enumerate(gpus_rmvpe):
+                    cmd = (
+                        '"%s" infer/modules/train/extract/extract_f0_rmvpe.py %s %s %s "%s/logs/%s" %s '
+                        % (
+                            config.python_cmd,
+                            leng,
+                            idx,
+                            n_g,
+                            now_dir,
+                            exp_dir,
+                            config.is_half,
+                        )
+                    )
+                    logger.info("Execute: " + cmd)
+                    p = Popen(
+                        cmd, shell=True, cwd=now_dir
+                    )  # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
+                    ps.append(p)
+                # 煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+                done = [False]
+                threading.Thread(
+                    target=if_done_multi,  #
+                    args=(
+                        done,
+                        ps,
+                    ),
+                ).start()
+            else:
+                cmd = (
+                    config.python_cmd
+                    + ' infer/modules/train/extract/extract_f0_rmvpe_dml.py "%s/logs/%s" '
+                    % (
+                        now_dir,
+                        exp_dir,
+                    )
+                )
+                logger.info("Execute: " + cmd)
+                p = Popen(
+                    cmd, shell=True, cwd=now_dir
+                )  # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
+                p.wait()
+                done = [True]
+        while 1:
+            with open(
+                "%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r"
+            ) as f:
+                yield (f.read())
+            sleep(1)
+            if done[0]:
+                break
+        with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+            log = f.read()
+        logger.info(log)
+        yield log
+    # 对不同part分别开多进程
+    """
+    n_part=int(sys.argv[1])
+    i_part=int(sys.argv[2])
+    i_gpu=sys.argv[3]
+    exp_dir=sys.argv[4]
+    os.environ["CUDA_VISIBLE_DEVICES"]=str(i_gpu)
+    """
+    leng = len(gpus)
+    ps = []
+    for idx, n_g in enumerate(gpus):
+        cmd = (
+            '"%s" infer/modules/train/extract_feature_print.py %s %s %s %s "%s/logs/%s" %s %s'
+            % (
+                config.python_cmd,
+                config.device,
+                leng,
+                idx,
+                n_g,
+                now_dir,
+                exp_dir,
+                version19,
+                config.is_half,
+            )
+        )
+        logger.info("Execute: " + cmd)
+        p = Popen(
+            cmd, shell=True, cwd=now_dir
+        )  # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
+        ps.append(p)
+    # 煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读
+    done = [False]
+    threading.Thread(
+        target=if_done_multi,
+        args=(
+            done,
+            ps,
+        ),
+    ).start()
+    while 1:
+        with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+            yield (f.read())
+        sleep(1)
+        if done[0]:
+            break
+    with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
+        log = f.read()
+    logger.info(log)
+    yield log
+
+
+def get_pretrained_models(path_str, f0_str, sr2):
+    if_pretrained_generator_exist = os.access(
+        "assets/pretrained%s/%sG%s.pth" % (path_str, f0_str, sr2), os.F_OK
+    )
+    if_pretrained_discriminator_exist = os.access(
+        "assets/pretrained%s/%sD%s.pth" % (path_str, f0_str, sr2), os.F_OK
+    )
+    if not if_pretrained_generator_exist:
+        logger.warning(
+            "assets/pretrained%s/%sG%s.pth not exist, will not use pretrained model",
+            path_str,
+            f0_str,
+            sr2,
+        )
+    if not if_pretrained_discriminator_exist:
+        logger.warning(
+            "assets/pretrained%s/%sD%s.pth not exist, will not use pretrained model",
+            path_str,
+            f0_str,
+            sr2,
+        )
+    return (
+        (
+            "assets/pretrained%s/%sG%s.pth" % (path_str, f0_str, sr2)
+            if if_pretrained_generator_exist
+            else ""
+        ),
+        (
+            "assets/pretrained%s/%sD%s.pth" % (path_str, f0_str, sr2)
+            if if_pretrained_discriminator_exist
+            else ""
+        ),
+    )
+
+
+def change_sr2(sr2, if_f0_3, version19):
+    path_str = "" if version19 == "v1" else "_v2"
+    f0_str = "f0" if if_f0_3 else ""
+    return get_pretrained_models(path_str, f0_str, sr2)
+
+
+def change_version19(sr2, if_f0_3, version19):
+    path_str = "" if version19 == "v1" else "_v2"
+    if sr2 == "32k" and version19 == "v1":
+        sr2 = "40k"
+    to_return_sr2 = (
+        {"choices": ["40k", "48k"], "__type__": "update", "value": sr2}
+        if version19 == "v1"
+        else {"choices": ["40k", "48k", "32k"], "__type__": "update", "value": sr2}
+    )
+    f0_str = "f0" if if_f0_3 else ""
+    return (
+        *get_pretrained_models(path_str, f0_str, sr2),
+        to_return_sr2,
+    )
+
+
+def change_f0(if_f0_3, sr2, version19):  # f0method8,pretrained_G14,pretrained_D15
+    path_str = "" if version19 == "v1" else "_v2"
+    return (
+        {"visible": if_f0_3, "__type__": "update"},
+        {"visible": if_f0_3, "__type__": "update"},
+        *get_pretrained_models(path_str, "f0" if if_f0_3 == True else "", sr2),
+    )
+
+
+# but3.click(click_train,[exp_dir1,sr2,if_f0_3,save_epoch10,total_epoch11,batch_size12,if_save_latest13,pretrained_G14,pretrained_D15,gpus16])
+def click_train(
+    exp_dir1,
+    sr2,
+    if_f0_3,
+    spk_id5,
+    save_epoch10,
+    total_epoch11,
+    batch_size12,
+    if_save_latest13,
+    pretrained_G14,
+    pretrained_D15,
+    gpus16,
+    if_cache_gpu17,
+    if_save_every_weights18,
+    version19,
+):
+    # 生成filelist
+    exp_dir = "%s/logs/%s" % (now_dir, exp_dir1)
+    os.makedirs(exp_dir, exist_ok=True)
+    gt_wavs_dir = "%s/0_gt_wavs" % (exp_dir)
+    feature_dir = (
+        "%s/3_feature256" % (exp_dir)
+        if version19 == "v1"
+        else "%s/3_feature768" % (exp_dir)
+    )
+    if if_f0_3:
+        f0_dir = "%s/2a_f0" % (exp_dir)
+        f0nsf_dir = "%s/2b-f0nsf" % (exp_dir)
+        names = (
+            set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)])
+            & set([name.split(".")[0] for name in os.listdir(feature_dir)])
+            & set([name.split(".")[0] for name in os.listdir(f0_dir)])
+            & set([name.split(".")[0] for name in os.listdir(f0nsf_dir)])
+        )
+    else:
+        names = set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)]) & set(
+            [name.split(".")[0] for name in os.listdir(feature_dir)]
+        )
+    opt = []
+    for name in names:
+        if if_f0_3:
+            opt.append(
+                "%s/%s.wav|%s/%s.npy|%s/%s.wav.npy|%s/%s.wav.npy|%s"
+                % (
+                    gt_wavs_dir.replace("\\", "\\\\"),
+                    name,
+                    feature_dir.replace("\\", "\\\\"),
+                    name,
+                    f0_dir.replace("\\", "\\\\"),
+                    name,
+                    f0nsf_dir.replace("\\", "\\\\"),
+                    name,
+                    spk_id5,
+                )
+            )
+        else:
+            opt.append(
+                "%s/%s.wav|%s/%s.npy|%s"
+                % (
+                    gt_wavs_dir.replace("\\", "\\\\"),
+                    name,
+                    feature_dir.replace("\\", "\\\\"),
+                    name,
+                    spk_id5,
+                )
+            )
+    fea_dim = 256 if version19 == "v1" else 768
+    if if_f0_3:
+        for _ in range(2):
+            opt.append(
+                "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s/logs/mute/2a_f0/mute.wav.npy|%s/logs/mute/2b-f0nsf/mute.wav.npy|%s"
+                % (now_dir, sr2, now_dir, fea_dim, now_dir, now_dir, spk_id5)
+            )
+    else:
+        for _ in range(2):
+            opt.append(
+                "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s"
+                % (now_dir, sr2, now_dir, fea_dim, spk_id5)
+            )
+    shuffle(opt)
+    with open("%s/filelist.txt" % exp_dir, "w") as f:
+        f.write("\n".join(opt))
+    logger.debug("Write filelist done")
+    # 生成config#无需生成config
+    # cmd = python_cmd + " train_nsf_sim_cache_sid_load_pretrain.py -e mi-test -sr 40k -f0 1 -bs 4 -g 0 -te 10 -se 5 -pg pretrained/f0G40k.pth -pd pretrained/f0D40k.pth -l 1 -c 0"
+    logger.info("Use gpus: %s", str(gpus16))
+    if pretrained_G14 == "":
+        logger.info("No pretrained Generator")
+    if pretrained_D15 == "":
+        logger.info("No pretrained Discriminator")
+    if version19 == "v1" or sr2 == "40k":
+        config_path = "v1/%s.json" % sr2
+    else:
+        config_path = "v2/%s.json" % sr2
+    config_save_path = os.path.join(exp_dir, "config.json")
+    if not pathlib.Path(config_save_path).exists():
+        with open(config_save_path, "w", encoding="utf-8") as f:
+            json.dump(
+                config.json_config[config_path],
+                f,
+                ensure_ascii=False,
+                indent=4,
+                sort_keys=True,
+            )
+            f.write("\n")
+    if gpus16:
+        cmd = (
+            '"%s" infer/modules/train/train.py -e "%s" -sr %s -f0 %s -bs %s -g %s -te %s -se %s %s %s -l %s -c %s -sw %s -v %s'
+            % (
+                config.python_cmd,
+                exp_dir1,
+                sr2,
+                1 if if_f0_3 else 0,
+                batch_size12,
+                gpus16,
+                total_epoch11,
+                save_epoch10,
+                "-pg %s" % pretrained_G14 if pretrained_G14 != "" else "",
+                "-pd %s" % pretrained_D15 if pretrained_D15 != "" else "",
+                1 if if_save_latest13 == i18n("是") else 0,
+                1 if if_cache_gpu17 == i18n("是") else 0,
+                1 if if_save_every_weights18 == i18n("是") else 0,
+                version19,
+            )
+        )
+    else:
+        cmd = (
+            '"%s" infer/modules/train/train.py -e "%s" -sr %s -f0 %s -bs %s -te %s -se %s %s %s -l %s -c %s -sw %s -v %s'
+            % (
+                config.python_cmd,
+                exp_dir1,
+                sr2,
+                1 if if_f0_3 else 0,
+                batch_size12,
+                total_epoch11,
+                save_epoch10,
+                "-pg %s" % pretrained_G14 if pretrained_G14 != "" else "",
+                "-pd %s" % pretrained_D15 if pretrained_D15 != "" else "",
+                1 if if_save_latest13 == i18n("是") else 0,
+                1 if if_cache_gpu17 == i18n("是") else 0,
+                1 if if_save_every_weights18 == i18n("是") else 0,
+                version19,
+            )
+        )
+    logger.info("Execute: " + cmd)
+    p = Popen(cmd, shell=True, cwd=now_dir)
+    p.wait()
+    return "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"
+
+
+# but4.click(train_index, [exp_dir1], info3)
+def train_index(exp_dir1, version19):
+    # exp_dir = "%s/logs/%s" % (now_dir, exp_dir1)
+    exp_dir = "logs/%s" % (exp_dir1)
+    os.makedirs(exp_dir, exist_ok=True)
+    feature_dir = (
+        "%s/3_feature256" % (exp_dir)
+        if version19 == "v1"
+        else "%s/3_feature768" % (exp_dir)
+    )
+    if not os.path.exists(feature_dir):
+        return "请先进行特征提取!"
+    listdir_res = list(os.listdir(feature_dir))
+    if len(listdir_res) == 0:
+        return "请先进行特征提取！"
+    infos = []
+    npys = []
+    for name in sorted(listdir_res):
+        phone = np.load("%s/%s" % (feature_dir, name))
+        npys.append(phone)
+    big_npy = np.concatenate(npys, 0)
+    big_npy_idx = np.arange(big_npy.shape[0])
+    np.random.shuffle(big_npy_idx)
+    big_npy = big_npy[big_npy_idx]
+    if big_npy.shape[0] > 2e5:
+        infos.append("Trying doing kmeans %s shape to 10k centers." % big_npy.shape[0])
+        yield "\n".join(infos)
+        try:
+            big_npy = (
+                MiniBatchKMeans(
+                    n_clusters=10000,
+                    verbose=True,
+                    batch_size=256 * config.n_cpu,
+                    compute_labels=False,
+                    init="random",
+                )
+                .fit(big_npy)
+                .cluster_centers_
+            )
+        except:
+            info = traceback.format_exc()
+            logger.info(info)
+            infos.append(info)
+            yield "\n".join(infos)
+
+    np.save("%s/total_fea.npy" % exp_dir, big_npy)
+    n_ivf = min(int(16 * np.sqrt(big_npy.shape[0])), big_npy.shape[0] // 39)
+    infos.append("%s,%s" % (big_npy.shape, n_ivf))
+    yield "\n".join(infos)
+    index = faiss.index_factory(256 if version19 == "v1" else 768, "IVF%s,Flat" % n_ivf)
+    # index = faiss.index_factory(256if version19=="v1"else 768, "IVF%s,PQ128x4fs,RFlat"%n_ivf)
+    infos.append("training")
+    yield "\n".join(infos)
+    index_ivf = faiss.extract_index_ivf(index)  #
+    index_ivf.nprobe = 1
+    index.train(big_npy)
+    faiss.write_index(
+        index,
+        "%s/trained_IVF%s_Flat_nprobe_%s_%s_%s.index"
+        % (exp_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19),
+    )
+    infos.append("adding")
+    yield "\n".join(infos)
+    batch_size_add = 8192
+    for i in range(0, big_npy.shape[0], batch_size_add):
+        index.add(big_npy[i : i + batch_size_add])
+    faiss.write_index(
+        index,
+        "%s/added_IVF%s_Flat_nprobe_%s_%s_%s.index"
+        % (exp_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19),
+    )
+    infos.append(
+        "成功构建索引 added_IVF%s_Flat_nprobe_%s_%s_%s.index"
+        % (n_ivf, index_ivf.nprobe, exp_dir1, version19)
+    )
+    try:
+        link = os.link if platform.system() == "Windows" else os.symlink
+        link(
+            "%s/added_IVF%s_Flat_nprobe_%s_%s_%s.index"
+            % (exp_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19),
+            "%s/%s_IVF%s_Flat_nprobe_%s_%s_%s.index"
+            % (
+                outside_index_root,
+                exp_dir1,
+                n_ivf,
+                index_ivf.nprobe,
+                exp_dir1,
+                version19,
+            ),
+        )
+        infos.append("链接索引到外部-%s" % (outside_index_root))
+    except:
+        infos.append("链接索引到外部-%s失败" % (outside_index_root))
+
+    # faiss.write_index(index, '%s/added_IVF%s_Flat_FastScan_%s.index'%(exp_dir,n_ivf,version19))
+    # infos.append("成功构建索引，added_IVF%s_Flat_FastScan_%s.index"%(n_ivf,version19))
+    yield "\n".join(infos)
+
+
+# but5.click(train1key, [exp_dir1, sr2, if_f0_3, trainset_dir4, spk_id5, gpus6, np7, f0method8, save_epoch10, total_epoch11, batch_size12, if_save_latest13, pretrained_G14, pretrained_D15, gpus16, if_cache_gpu17], info3)
+def train1key(
+    exp_dir1,
+    sr2,
+    if_f0_3,
+    trainset_dir4,
+    spk_id5,
+    np7,
+    f0method8,
+    save_epoch10,
+    total_epoch11,
+    batch_size12,
+    if_save_latest13,
+    pretrained_G14,
+    pretrained_D15,
+    gpus16,
+    if_cache_gpu17,
+    if_save_every_weights18,
+    version19,
+    gpus_rmvpe,
+):
+    infos = []
+
+    def get_info_str(strr):
+        infos.append(strr)
+        return "\n".join(infos)
+
+    # step1:处理数据
+    yield get_info_str(i18n("step1:正在处理数据"))
+    [get_info_str(_) for _ in preprocess_dataset(trainset_dir4, exp_dir1, sr2, np7)]
+
+    # step2a:提取音高
+    yield get_info_str(i18n("step2:正在提取音高&正在提取特征"))
+    [
+        get_info_str(_)
+        for _ in extract_f0_feature(
+            gpus16, np7, f0method8, if_f0_3, exp_dir1, version19, gpus_rmvpe
+        )
+    ]
+
+    # step3a:训练模型
+    yield get_info_str(i18n("step3a:正在训练模型"))
+    click_train(
+        exp_dir1,
+        sr2,
+        if_f0_3,
+        spk_id5,
+        save_epoch10,
+        total_epoch11,
+        batch_size12,
+        if_save_latest13,
+        pretrained_G14,
+        pretrained_D15,
+        gpus16,
+        if_cache_gpu17,
+        if_save_every_weights18,
+        version19,
+    )
+    yield get_info_str(
+        i18n("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")
+    )
+
+    # step3b:训练索引
+    [get_info_str(_) for _ in train_index(exp_dir1, version19)]
+    yield get_info_str(i18n("全流程结束！"))
+
+
+#                    ckpt_path2.change(change_info_,[ckpt_path2],[sr__,if_f0__])
+def change_info_(ckpt_path):
+    if not os.path.exists(ckpt_path.replace(os.path.basename(ckpt_path), "train.log")):
+        return {"__type__": "update"}, {"__type__": "update"}, {"__type__": "update"}
+    try:
+        with open(
+            ckpt_path.replace(os.path.basename(ckpt_path), "train.log"), "r"
+        ) as f:
+            info = eval(f.read().strip("\n").split("\n")[0].split("\t")[-1])
+            sr, f0 = info["sample_rate"], info["if_f0"]
+            version = "v2" if ("version" in info and info["version"] == "v2") else "v1"
+            return sr, str(f0), version
+    except:
+        traceback.print_exc()
+        return {"__type__": "update"}, {"__type__": "update"}, {"__type__": "update"}
+
+
+F0GPUVisible = config.dml == False
+
+
+def change_f0_method(f0method8):
+    if f0method8 == "rmvpe_gpu":
+        visible = F0GPUVisible
+    else:
+        visible = False
+    return {"visible": visible, "__type__": "update"}
+
+
+with gr.Blocks(title="RVC WebUI") as app:
+    gr.Markdown("## RVC WebUI")
+    gr.Markdown(
+        value=i18n(
+            "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责. <br>如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录<b>LICENSE</b>."
+        )
+    )
+    with gr.Tabs():
+        with gr.TabItem(i18n("模型推理")):
+            with gr.Row():
+                sid0 = gr.Dropdown(label=i18n("推理音色"), choices=sorted(names))
+                with gr.Column():
+                    refresh_button = gr.Button(
+                        i18n("刷新音色列表和索引路径"), variant="primary"
+                    )
+                    clean_button = gr.Button(i18n("卸载音色省显存"), variant="primary")
+                spk_item = gr.Slider(
+                    minimum=0,
+                    maximum=2333,
+                    step=1,
+                    label=i18n("请选择说话人id"),
+                    value=0,
+                    visible=False,
+                    interactive=True,
+                )
+                clean_button.click(
+                    fn=clean, inputs=[], outputs=[sid0], api_name="infer_clean"
+                )
+            with gr.TabItem(i18n("单次推理")):
+                with gr.Group():
+                    with gr.Row():
+                        with gr.Column():
+                            vc_transform0 = gr.Number(
+                                label=i18n("变调(整数, 半音数量, 升八度12降八度-12)"),
+                                value=0,
+                            )
+                            input_audio0 = gr.Textbox(
+                                label=i18n(
+                                    "输入待处理音频文件路径(默认是正确格式示例)"
+                                ),
+                                placeholder="C:\\Users\\Desktop\\audio_example.wav",
+                            )
+                            file_index1 = gr.Textbox(
+                                label=i18n(
+                                    "特征检索库文件路径,为空则使用下拉的选择结果"
+                                ),
+                                placeholder="C:\\Users\\Desktop\\model_example.index",
+                                interactive=True,
+                            )
+                            file_index2 = gr.Dropdown(
+                                label=i18n("自动检测index路径,下拉式选择(dropdown)"),
+                                choices=sorted(index_paths),
+                                interactive=True,
+                            )
+                            f0method0 = gr.Radio(
+                                label=i18n(
+                                    "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU,rmvpe效果最好且微吃GPU"
+                                ),
+                                choices=(
+                                    ["pm", "harvest", "crepe", "rmvpe"]
+                                    if config.dml == False
+                                    else ["pm", "harvest", "rmvpe"]
+                                ),
+                                value="rmvpe",
+                                interactive=True,
+                            )
+
+                        with gr.Column():
+                            resample_sr0 = gr.Slider(
+                                minimum=0,
+                                maximum=48000,
+                                label=i18n("后处理重采样至最终采样率，0为不进行重采样"),
+                                value=0,
+                                step=1,
+                                interactive=True,
+                            )
+                            rms_mix_rate0 = gr.Slider(
+                                minimum=0,
+                                maximum=1,
+                                label=i18n(
+                                    "输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络"
+                                ),
+                                value=0.25,
+                                interactive=True,
+                            )
+                            protect0 = gr.Slider(
+                                minimum=0,
+                                maximum=0.5,
+                                label=i18n(
+                                    "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果"
+                                ),
+                                value=0.33,
+                                step=0.01,
+                                interactive=True,
+                            )
+                            filter_radius0 = gr.Slider(
+                                minimum=0,
+                                maximum=7,
+                                label=i18n(
+                                    ">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音"
+                                ),
+                                value=3,
+                                step=1,
+                                interactive=True,
+                            )
+                            index_rate1 = gr.Slider(
+                                minimum=0,
+                                maximum=1,
+                                label=i18n("检索特征占比"),
+                                value=0.75,
+                                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"
+                                ),
+                                visible=False,
+                            )
+
+                            refresh_button.click(
+                                fn=change_choices,
+                                inputs=[],
+                                outputs=[sid0, file_index2],
+                                api_name="infer_refresh",
+                            )
+                            # file_big_npy1 = gr.Textbox(
+                            #     label=i18n("特征文件路径"),
+                            #     value="E:\\codes\py39\\vits_vc_gpu_train\\logs\\mi-test-1key\\total_fea.npy",
+                            #     interactive=True,
+                            # )
+                with gr.Group():
+                    with gr.Column():
+                        but0 = gr.Button(i18n("转换"), variant="primary")
+                        with gr.Row():
+                            vc_output1 = gr.Textbox(label=i18n("输出信息"))
+                            vc_output2 = gr.Audio(
+                                label=i18n("输出音频(右下角三个点,点了可以下载)")
+                            )
+
+                        but0.click(
+                            vc.vc_single,
+                            [
+                                spk_item,
+                                input_audio0,
+                                vc_transform0,
+                                f0_file,
+                                f0method0,
+                                file_index1,
+                                file_index2,
+                                # file_big_npy1,
+                                index_rate1,
+                                filter_radius0,
+                                resample_sr0,
+                                rms_mix_rate0,
+                                protect0,
+                            ],
+                            [vc_output1, vc_output2],
+                            api_name="infer_convert",
+                        )
+            with gr.TabItem(i18n("批量推理")):
+                gr.Markdown(
+                    value=i18n(
+                        "批量转换, 输入待转换音频文件夹, 或上传多个音频文件, 在指定文件夹(默认opt)下输出转换的音频. "
+                    )
+                )
+                with gr.Row():
+                    with gr.Column():
+                        vc_transform1 = gr.Number(
+                            label=i18n("变调(整数, 半音数量, 升八度12降八度-12)"),
+                            value=0,
+                        )
+                        opt_input = gr.Textbox(
+                            label=i18n("指定输出文件夹"), value="opt"
+                        )
+                        file_index3 = gr.Textbox(
+                            label=i18n("特征检索库文件路径,为空则使用下拉的选择结果"),
+                            value="",
+                            interactive=True,
+                        )
+                        file_index4 = gr.Dropdown(
+                            label=i18n("自动检测index路径,下拉式选择(dropdown)"),
+                            choices=sorted(index_paths),
+                            interactive=True,
+                        )
+                        f0method1 = gr.Radio(
+                            label=i18n(
+                                "选择音高提取算法,输入歌声可用pm提速,harvest低音好但巨慢无比,crepe效果好但吃GPU,rmvpe效果最好且微吃GPU"
+                            ),
+                            choices=(
+                                ["pm", "harvest", "crepe", "rmvpe"]
+                                if config.dml == False
+                                else ["pm", "harvest", "rmvpe"]
+                            ),
+                            value="rmvpe",
+                            interactive=True,
+                        )
+                        format1 = gr.Radio(
+                            label=i18n("导出文件格式"),
+                            choices=["wav", "flac", "mp3", "m4a"],
+                            value="wav",
+                            interactive=True,
+                        )
+
+                        refresh_button.click(
+                            fn=lambda: change_choices()[1],
+                            inputs=[],
+                            outputs=file_index4,
+                            api_name="infer_refresh_batch",
+                        )
+                        # file_big_npy2 = gr.Textbox(
+                        #     label=i18n("特征文件路径"),
+                        #     value="E:\\codes\\py39\\vits_vc_gpu_train\\logs\\mi-test-1key\\total_fea.npy",
+                        #     interactive=True,
+                        # )
+
+                    with gr.Column():
+                        resample_sr1 = gr.Slider(
+                            minimum=0,
+                            maximum=48000,
+                            label=i18n("后处理重采样至最终采样率，0为不进行重采样"),
+                            value=0,
+                            step=1,
+                            interactive=True,
+                        )
+                        rms_mix_rate1 = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            label=i18n(
+                                "输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络"
+                            ),
+                            value=1,
+                            interactive=True,
+                        )
+                        protect1 = gr.Slider(
+                            minimum=0,
+                            maximum=0.5,
+                            label=i18n(
+                                "保护清辅音和呼吸声，防止电音撕裂等artifact，拉满0.5不开启，调低加大保护力度但可能降低索引效果"
+                            ),
+                            value=0.33,
+                            step=0.01,
+                            interactive=True,
+                        )
+                        filter_radius1 = gr.Slider(
+                            minimum=0,
+                            maximum=7,
+                            label=i18n(
+                                ">=3则使用对harvest音高识别的结果使用中值滤波，数值为滤波半径，使用可以削弱哑音"
+                            ),
+                            value=3,
+                            step=1,
+                            interactive=True,
+                        )
+                        index_rate2 = gr.Slider(
+                            minimum=0,
+                            maximum=1,
+                            label=i18n("检索特征占比"),
+                            value=1,
+                            interactive=True,
+                        )
+                with gr.Row():
+                    dir_input = gr.Textbox(
+                        label=i18n(
+                            "输入待处理音频文件夹路径(去文件管理器地址栏拷就行了)"
+                        ),
+                        placeholder="C:\\Users\\Desktop\\input_vocal_dir",
+                    )
+                    inputs = gr.File(
+                        file_count="multiple",
+                        label=i18n("也可批量输入音频文件, 二选一, 优先读文件夹"),
+                    )
+
+                with gr.Row():
+                    but1 = gr.Button(i18n("转换"), variant="primary")
+                    vc_output3 = gr.Textbox(label=i18n("输出信息"))
+
+                    but1.click(
+                        vc.vc_multi,
+                        [
+                            spk_item,
+                            dir_input,
+                            opt_input,
+                            inputs,
+                            vc_transform1,
+                            f0method1,
+                            file_index3,
+                            file_index4,
+                            # file_big_npy2,
+                            index_rate2,
+                            filter_radius1,
+                            resample_sr1,
+                            rms_mix_rate1,
+                            protect1,
+                            format1,
+                        ],
+                        [vc_output3],
+                        api_name="infer_convert_batch",
+                    )
+                sid0.change(
+                    fn=vc.get_vc,
+                    inputs=[sid0, protect0, protect1],
+                    outputs=[spk_item, protect0, protect1, file_index2, file_index4],
+                    api_name="infer_change_voice",
+                )
+        with gr.TabItem(i18n("伴奏人声分离&去混响&去回声")):
+            with gr.Group():
+                gr.Markdown(
+                    value=i18n(
+                        "人声伴奏分离批量处理， 使用UVR5模型。 <br>合格的文件夹路径格式举例： E:\\codes\\py39\\vits_vc_gpu\\白鹭霜华测试样例(去文件管理器地址栏拷就行了)。 <br>模型分为三类： <br>1、保留人声：不带和声的音频选这个，对主人声保留比HP5更好。内置HP2和HP3两个模型，HP3可能轻微漏伴奏但对主人声保留比HP2稍微好一丁点； <br>2、仅保留主人声：带和声的音频选这个，对主人声可能有削弱。内置HP5一个模型； <br> 3、去混响、去延迟模型（by FoxJoy）：<br>  (1)MDX-Net(onnx_dereverb):对于双通道混响是最好的选择，不能去除单通道混响；<br>&emsp;(234)DeEcho:去除延迟效果。Aggressive比Normal去除得更彻底，DeReverb额外去除混响，可去除单声道混响，但是对高频重的板式混响去不干净。<br>去混响/去延迟，附：<br>1、DeEcho-DeReverb模型的耗时是另外2个DeEcho模型的接近2倍；<br>2、MDX-Net-Dereverb模型挺慢的；<br>3、个人推荐的最干净的配置是先MDX-Net再DeEcho-Aggressive。"
+                    )
+                )
+                with gr.Row():
+                    with gr.Column():
+                        dir_wav_input = gr.Textbox(
+                            label=i18n("输入待处理音频文件夹路径"),
+                            placeholder="C:\\Users\\Desktop\\todo-songs",
+                        )
+                        wav_inputs = gr.File(
+                            file_count="multiple",
+                            label=i18n("也可批量输入音频文件, 二选一, 优先读文件夹"),
+                        )
+                    with gr.Column():
+                        model_choose = gr.Dropdown(
+                            label=i18n("模型"), choices=uvr5_names
+                        )
+                        agg = gr.Slider(
+                            minimum=0,
+                            maximum=20,
+                            step=1,
+                            label="人声提取激进程度",
+                            value=10,
+                            interactive=True,
+                            visible=False,  # 先不开放调整
+                        )
+                        opt_vocal_root = gr.Textbox(
+                            label=i18n("指定输出主人声文件夹"), value="opt"
+                        )
+                        opt_ins_root = gr.Textbox(
+                            label=i18n("指定输出非主人声文件夹"), value="opt"
+                        )
+                        format0 = gr.Radio(
+                            label=i18n("导出文件格式"),
+                            choices=["wav", "flac", "mp3", "m4a"],
+                            value="flac",
+                            interactive=True,
+                        )
+                    but2 = gr.Button(i18n("转换"), variant="primary")
+                    vc_output4 = gr.Textbox(label=i18n("输出信息"))
+                    but2.click(
+                        uvr,
+                        [
+                            model_choose,
+                            dir_wav_input,
+                            opt_vocal_root,
+                            wav_inputs,
+                            opt_ins_root,
+                            agg,
+                            format0,
+                        ],
+                        [vc_output4],
+                        api_name="uvr_convert",
+                    )
+        with gr.TabItem(i18n("训练")):
+            gr.Markdown(
+                value=i18n(
+                    "step1: 填写实验配置. 实验数据放在logs下, 每个实验一个文件夹, 需手工输入实验名路径, 内含实验配置, 日志, 训练得到的模型文件. "
+                )
+            )
+            with gr.Row():
+                exp_dir1 = gr.Textbox(label=i18n("输入实验名"), value="mi-test")
+                sr2 = gr.Radio(
+                    label=i18n("目标采样率"),
+                    choices=["40k", "48k"],
+                    value="40k",
+                    interactive=True,
+                )
+                if_f0_3 = gr.Radio(
+                    label=i18n("模型是否带音高指导(唱歌一定要, 语音可以不要)"),
+                    choices=[True, False],
+                    value=True,
+                    interactive=True,
+                )
+                version19 = gr.Radio(
+                    label=i18n("版本"),
+                    choices=["v1", "v2"],
+                    value="v2",
+                    interactive=True,
+                    visible=True,
+                )
+                np7 = gr.Slider(
+                    minimum=0,
+                    maximum=config.n_cpu,
+                    step=1,
+                    label=i18n("提取音高和处理数据使用的CPU进程数"),
+                    value=int(np.ceil(config.n_cpu / 1.5)),
+                    interactive=True,
+                )
+            with gr.Group():  # 暂时单人的, 后面支持最多4人的#数据处理
+                gr.Markdown(
+                    value=i18n(
+                        "step2a: 自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练. "
+                    )
+                )
+                with gr.Row():
+                    trainset_dir4 = gr.Textbox(
+                        label=i18n("输入训练文件夹路径"),
+                        value=i18n("E:\\语音音频+标注\\米津玄师\\src"),
+                    )
+                    spk_id5 = gr.Slider(
+                        minimum=0,
+                        maximum=4,
+                        step=1,
+                        label=i18n("请指定说话人id"),
+                        value=0,
+                        interactive=True,
+                    )
+                    but1 = gr.Button(i18n("处理数据"), variant="primary")
+                    info1 = gr.Textbox(label=i18n("输出信息"), value="")
+                    but1.click(
+                        preprocess_dataset,
+                        [trainset_dir4, exp_dir1, sr2, np7],
+                        [info1],
+                        api_name="train_preprocess",
+                    )
+            with gr.Group():
+                gr.Markdown(
+                    value=i18n(
+                        "step2b: 使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号)"
+                    )
+                )
+                with gr.Row():
+                    with gr.Column():
+                        gpus6 = gr.Textbox(
+                            label=i18n(
+                                "以-分隔输入使用的卡号, 例如   0-1-2   使用卡0和卡1和卡2"
+                            ),
+                            value=gpus,
+                            interactive=True,
+                            visible=F0GPUVisible,
+                        )
+                        gpu_info9 = gr.Textbox(
+                            label=i18n("显卡信息"), value=gpu_info, visible=F0GPUVisible
+                        )
+                    with gr.Column():
+                        f0method8 = gr.Radio(
+                            label=i18n(
+                                "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢,rmvpe效果最好且微吃CPU/GPU"
+                            ),
+                            choices=["pm", "harvest", "dio", "rmvpe", "rmvpe_gpu"],
+                            value="rmvpe_gpu",
+                            interactive=True,
+                        )
+                        gpus_rmvpe = gr.Textbox(
+                            label=i18n(
+                                "rmvpe卡号配置：以-分隔输入使用的不同进程卡号,例如0-0-1使用在卡0上跑2个进程并在卡1上跑1个进程"
+                            ),
+                            value="%s-%s" % (gpus, gpus),
+                            interactive=True,
+                            visible=F0GPUVisible,
+                        )
+                    but2 = gr.Button(i18n("特征提取"), variant="primary")
+                    info2 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+                    f0method8.change(
+                        fn=change_f0_method,
+                        inputs=[f0method8],
+                        outputs=[gpus_rmvpe],
+                    )
+                    but2.click(
+                        extract_f0_feature,
+                        [
+                            gpus6,
+                            np7,
+                            f0method8,
+                            if_f0_3,
+                            exp_dir1,
+                            version19,
+                            gpus_rmvpe,
+                        ],
+                        [info2],
+                        api_name="train_extract_f0_feature",
+                    )
+            with gr.Group():
+                gr.Markdown(value=i18n("step3: 填写训练设置, 开始训练模型和索引"))
+                with gr.Row():
+                    save_epoch10 = gr.Slider(
+                        minimum=1,
+                        maximum=50,
+                        step=1,
+                        label=i18n("保存频率save_every_epoch"),
+                        value=5,
+                        interactive=True,
+                    )
+                    total_epoch11 = gr.Slider(
+                        minimum=2,
+                        maximum=1000,
+                        step=1,
+                        label=i18n("总训练轮数total_epoch"),
+                        value=20,
+                        interactive=True,
+                    )
+                    batch_size12 = gr.Slider(
+                        minimum=1,
+                        maximum=40,
+                        step=1,
+                        label=i18n("每张显卡的batch_size"),
+                        value=default_batch_size,
+                        interactive=True,
+                    )
+                    if_save_latest13 = gr.Radio(
+                        label=i18n("是否仅保存最新的ckpt文件以节省硬盘空间"),
+                        choices=[i18n("是"), i18n("否")],
+                        value=i18n("否"),
+                        interactive=True,
+                    )
+                    if_cache_gpu17 = gr.Radio(
+                        label=i18n(
+                            "是否缓存所有训练集至显存. 10min以下小数据可缓存以加速训练, 大数据缓存会炸显存也加不了多少速"
+                        ),
+                        choices=[i18n("是"), i18n("否")],
+                        value=i18n("否"),
+                        interactive=True,
+                    )
+                    if_save_every_weights18 = gr.Radio(
+                        label=i18n(
+                            "是否在每次保存时间点将最终小模型保存至weights文件夹"
+                        ),
+                        choices=[i18n("是"), i18n("否")],
+                        value=i18n("否"),
+                        interactive=True,
+                    )
+                with gr.Row():
+                    pretrained_G14 = gr.Textbox(
+                        label=i18n("加载预训练底模G路径"),
+                        value="assets/pretrained_v2/f0G40k.pth",
+                        interactive=True,
+                    )
+                    pretrained_D15 = gr.Textbox(
+                        label=i18n("加载预训练底模D路径"),
+                        value="assets/pretrained_v2/f0D40k.pth",
+                        interactive=True,
+                    )
+                    sr2.change(
+                        change_sr2,
+                        [sr2, if_f0_3, version19],
+                        [pretrained_G14, pretrained_D15],
+                    )
+                    version19.change(
+                        change_version19,
+                        [sr2, if_f0_3, version19],
+                        [pretrained_G14, pretrained_D15, sr2],
+                    )
+                    if_f0_3.change(
+                        change_f0,
+                        [if_f0_3, sr2, version19],
+                        [f0method8, gpus_rmvpe, pretrained_G14, pretrained_D15],
+                    )
+                    gpus16 = gr.Textbox(
+                        label=i18n(
+                            "以-分隔输入使用的卡号, 例如   0-1-2   使用卡0和卡1和卡2"
+                        ),
+                        value=gpus,
+                        interactive=True,
+                    )
+                    but3 = gr.Button(i18n("训练模型"), variant="primary")
+                    but4 = gr.Button(i18n("训练特征索引"), variant="primary")
+                    but5 = gr.Button(i18n("一键训练"), variant="primary")
+                    info3 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=10)
+                    but3.click(
+                        click_train,
+                        [
+                            exp_dir1,
+                            sr2,
+                            if_f0_3,
+                            spk_id5,
+                            save_epoch10,
+                            total_epoch11,
+                            batch_size12,
+                            if_save_latest13,
+                            pretrained_G14,
+                            pretrained_D15,
+                            gpus16,
+                            if_cache_gpu17,
+                            if_save_every_weights18,
+                            version19,
+                        ],
+                        info3,
+                        api_name="train_start",
+                    )
+                    but4.click(train_index, [exp_dir1, version19], info3)
+                    but5.click(
+                        train1key,
+                        [
+                            exp_dir1,
+                            sr2,
+                            if_f0_3,
+                            trainset_dir4,
+                            spk_id5,
+                            np7,
+                            f0method8,
+                            save_epoch10,
+                            total_epoch11,
+                            batch_size12,
+                            if_save_latest13,
+                            pretrained_G14,
+                            pretrained_D15,
+                            gpus16,
+                            if_cache_gpu17,
+                            if_save_every_weights18,
+                            version19,
+                            gpus_rmvpe,
+                        ],
+                        info3,
+                        api_name="train_start_all",
+                    )
+
+        with gr.TabItem(i18n("ckpt处理")):
+            with gr.Group():
+                gr.Markdown(value=i18n("模型融合, 可用于测试音色融合"))
+                with gr.Row():
+                    ckpt_a = gr.Textbox(
+                        label=i18n("A模型路径"), value="", interactive=True
+                    )
+                    ckpt_b = gr.Textbox(
+                        label=i18n("B模型路径"), value="", interactive=True
+                    )
+                    alpha_a = gr.Slider(
+                        minimum=0,
+                        maximum=1,
+                        label=i18n("A模型权重"),
+                        value=0.5,
+                        interactive=True,
+                    )
+                with gr.Row():
+                    sr_ = gr.Radio(
+                        label=i18n("目标采样率"),
+                        choices=["40k", "48k"],
+                        value="40k",
+                        interactive=True,
+                    )
+                    if_f0_ = gr.Radio(
+                        label=i18n("模型是否带音高指导"),
+                        choices=[i18n("是"), i18n("否")],
+                        value=i18n("是"),
+                        interactive=True,
+                    )
+                    info__ = gr.Textbox(
+                        label=i18n("要置入的模型信息"),
+                        value="",
+                        max_lines=8,
+                        interactive=True,
+                    )
+                    name_to_save0 = gr.Textbox(
+                        label=i18n("保存的模型名不带后缀"),
+                        value="",
+                        max_lines=1,
+                        interactive=True,
+                    )
+                    version_2 = gr.Radio(
+                        label=i18n("模型版本型号"),
+                        choices=["v1", "v2"],
+                        value="v1",
+                        interactive=True,
+                    )
+                with gr.Row():
+                    but6 = gr.Button(i18n("融合"), variant="primary")
+                    info4 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+                but6.click(
+                    merge,
+                    [
+                        ckpt_a,
+                        ckpt_b,
+                        alpha_a,
+                        sr_,
+                        if_f0_,
+                        info__,
+                        name_to_save0,
+                        version_2,
+                    ],
+                    info4,
+                    api_name="ckpt_merge",
+                )  # def merge(path1,path2,alpha1,sr,f0,info):
+            with gr.Group():
+                gr.Markdown(
+                    value=i18n("修改模型信息(仅支持weights文件夹下提取的小模型文件)")
+                )
+                with gr.Row():
+                    ckpt_path0 = gr.Textbox(
+                        label=i18n("模型路径"), value="", interactive=True
+                    )
+                    info_ = gr.Textbox(
+                        label=i18n("要改的模型信息"),
+                        value="",
+                        max_lines=8,
+                        interactive=True,
+                    )
+                    name_to_save1 = gr.Textbox(
+                        label=i18n("保存的文件名, 默认空为和源文件同名"),
+                        value="",
+                        max_lines=8,
+                        interactive=True,
+                    )
+                with gr.Row():
+                    but7 = gr.Button(i18n("修改"), variant="primary")
+                    info5 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+                but7.click(
+                    change_info,
+                    [ckpt_path0, info_, name_to_save1],
+                    info5,
+                    api_name="ckpt_modify",
+                )
+            with gr.Group():
+                gr.Markdown(
+                    value=i18n("查看模型信息(仅支持weights文件夹下提取的小模型文件)")
+                )
+                with gr.Row():
+                    ckpt_path1 = gr.Textbox(
+                        label=i18n("模型路径"), value="", interactive=True
+                    )
+                    but8 = gr.Button(i18n("查看"), variant="primary")
+                    info6 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+                but8.click(show_info, [ckpt_path1], info6, api_name="ckpt_show")
+            with gr.Group():
+                gr.Markdown(
+                    value=i18n(
+                        "模型提取(输入logs文件夹下大文件模型路径),适用于训一半不想训了模型没有自动提取保存小文件模型,或者想测试中间模型的情况"
+                    )
+                )
+                with gr.Row():
+                    ckpt_path2 = gr.Textbox(
+                        label=i18n("模型路径"),
+                        value="E:\\codes\\py39\\logs\\mi-test_f0_48k\\G_23333.pth",
+                        interactive=True,
+                    )
+                    save_name = gr.Textbox(
+                        label=i18n("保存名"), value="", interactive=True
+                    )
+                    sr__ = gr.Radio(
+                        label=i18n("目标采样率"),
+                        choices=["32k", "40k", "48k"],
+                        value="40k",
+                        interactive=True,
+                    )
+                    if_f0__ = gr.Radio(
+                        label=i18n("模型是否带音高指导,1是0否"),
+                        choices=["1", "0"],
+                        value="1",
+                        interactive=True,
+                    )
+                    version_1 = gr.Radio(
+                        label=i18n("模型版本型号"),
+                        choices=["v1", "v2"],
+                        value="v2",
+                        interactive=True,
+                    )
+                    info___ = gr.Textbox(
+                        label=i18n("要置入的模型信息"),
+                        value="",
+                        max_lines=8,
+                        interactive=True,
+                    )
+                    but9 = gr.Button(i18n("提取"), variant="primary")
+                    info7 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8)
+                    ckpt_path2.change(
+                        change_info_, [ckpt_path2], [sr__, if_f0__, version_1]
+                    )
+                but9.click(
+                    extract_small_model,
+                    [ckpt_path2, save_name, sr__, if_f0__, info___, version_1],
+                    info7,
+                    api_name="ckpt_extract",
+                )
+
+        with gr.TabItem(i18n("Onnx导出")):
+            with gr.Row():
+                ckpt_dir = gr.Textbox(
+                    label=i18n("RVC模型路径"), value="", interactive=True
+                )
+            with gr.Row():
+                onnx_dir = gr.Textbox(
+                    label=i18n("Onnx输出路径"), value="", interactive=True
+                )
+            with gr.Row():
+                infoOnnx = gr.Label(label="info")
+            with gr.Row():
+                butOnnx = gr.Button(i18n("导出Onnx模型"), variant="primary")
+            butOnnx.click(
+                export_onnx, [ckpt_dir, onnx_dir], infoOnnx, api_name="export_onnx"
+            )
+
+        tab_faq = i18n("常见问题解答")
+        with gr.TabItem(tab_faq):
+            try:
+                if tab_faq == "常见问题解答":
+                    with open("docs/cn/faq.md", "r", encoding="utf8") as f:
+                        info = f.read()
+                else:
+                    with open("docs/en/faq_en.md", "r", encoding="utf8") as f:
+                        info = f.read()
+                gr.Markdown(value=info)
+            except:
+                gr.Markdown(traceback.format_exc())
+
+    if config.iscolab:
+        app.queue(concurrency_count=511, max_size=1022).launch(share=True)
+    else:
+        app.queue(concurrency_count=511, max_size=1022).launch(
+            server_name="0.0.0.0",
+            inbrowser=not config.noautoopen,
+            server_port=config.listen_port,
+            quiet=True,
+        )

infer_batch_rvc.py

@@ -0,0 +1,72 @@
+import argparse
+import os
+import sys
+
+print("Command-line arguments:", sys.argv)
+
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+import sys
+
+import tqdm as tq
+from dotenv import load_dotenv
+from scipy.io import wavfile
+
+from config import Config
+from modules import VC
+
+
+def arg_parse() -> tuple:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--f0up_key", type=int, default=0)
+    parser.add_argument("--input_path", type=str, help="input path")
+    parser.add_argument("--index_path", type=str, help="index path")
+    parser.add_argument("--f0method", type=str, default="harvest", help="harvest or pm")
+    parser.add_argument("--opt_path", type=str, help="opt path")
+    parser.add_argument("--model_name", type=str, help="store in assets/weight_root")
+    parser.add_argument("--index_rate", type=float, default=0.66, help="index rate")
+    parser.add_argument("--device", type=str, help="device")
+    parser.add_argument("--is_half", type=bool, help="use half -> True")
+    parser.add_argument("--filter_radius", type=int, default=3, help="filter radius")
+    parser.add_argument("--resample_sr", type=int, default=0, help="resample sr")
+    parser.add_argument("--rms_mix_rate", type=float, default=1, help="rms mix rate")
+    parser.add_argument("--protect", type=float, default=0.33, help="protect")
+
+    args = parser.parse_args()
+    sys.argv = sys.argv[:1]
+
+    return args
+
+
+def main():
+    load_dotenv()
+    args = arg_parse()
+    config = Config()
+    config.device = args.device if args.device else config.device
+    config.is_half = args.is_half if args.is_half else config.is_half
+    vc = VC(config)
+    vc.get_vc(args.model_name)
+    audios = os.listdir(args.input_path)
+    for file in tq.tqdm(audios):
+        if file.endswith(".wav"):
+            file_path = os.path.join(args.input_path, file)
+            _, wav_opt = vc.vc_single(
+                0,
+                file_path,
+                args.f0up_key,
+                None,
+                args.f0method,
+                args.index_path,
+                None,
+                args.index_rate,
+                args.filter_radius,
+                args.resample_sr,
+                args.rms_mix_rate,
+                args.protect,
+            )
+            out_path = os.path.join(args.opt_path, file)
+            wavfile.write(out_path, wav_opt[0], wav_opt[1])
+
+
+if __name__ == "__main__":
+    main()

infer_cli.py

@@ -0,0 +1,67 @@
+import argparse
+import os
+import sys
+
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+from dotenv import load_dotenv
+from scipy.io import wavfile
+
+from configs.config import Config
+from infer.modules.vc.modules import VC
+
+####
+# USAGE
+#
+# In your Terminal or CMD or whatever
+
+
+def arg_parse() -> tuple:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--f0up_key", type=int, default=0)
+    parser.add_argument("--input_path", type=str, help="input path")
+    parser.add_argument("--index_path", type=str, help="index path")
+    parser.add_argument("--f0method", type=str, default="harvest", help="harvest or pm")
+    parser.add_argument("--opt_path", type=str, help="opt path")
+    parser.add_argument("--model_name", type=str, help="store in assets/weight_root")
+    parser.add_argument("--index_rate", type=float, default=0.66, help="index rate")
+    parser.add_argument("--device", type=str, help="device")
+    parser.add_argument("--is_half", type=bool, help="use half -> True")
+    parser.add_argument("--filter_radius", type=int, default=3, help="filter radius")
+    parser.add_argument("--resample_sr", type=int, default=0, help="resample sr")
+    parser.add_argument("--rms_mix_rate", type=float, default=1, help="rms mix rate")
+    parser.add_argument("--protect", type=float, default=0.33, help="protect")
+
+    args = parser.parse_args()
+    sys.argv = sys.argv[:1]
+
+    return args
+
+
+def main():
+    load_dotenv()
+    args = arg_parse()
+    config = Config()
+    config.device = args.device if args.device else config.device
+    config.is_half = args.is_half if args.is_half else config.is_half
+    vc = VC(config)
+    vc.get_vc(args.model_name)
+    _, wav_opt = vc.vc_single(
+        0,
+        args.input_path,
+        args.f0up_key,
+        None,
+        args.f0method,
+        args.index_path,
+        None,
+        args.index_rate,
+        args.filter_radius,
+        args.resample_sr,
+        args.rms_mix_rate,
+        args.protect,
+    )
+    wavfile.write(args.opt_path, wav_opt[0], wav_opt[1])
+
+
+if __name__ == "__main__":
+    main()

modules.py

@@ -0,0 +1,304 @@
+import traceback
+import logging
+
+logger = logging.getLogger(__name__)
+
+import numpy as np
+import soundfile as sf
+import torch
+from io import BytesIO
+
+from infer.lib.audio import load_audio, wav2
+from infer.lib.infer_pack.models import (
+    SynthesizerTrnMs256NSFsid,
+    SynthesizerTrnMs256NSFsid_nono,
+    SynthesizerTrnMs768NSFsid,
+    SynthesizerTrnMs768NSFsid_nono,
+)
+from infer.modules.vc.pipeline import Pipeline
+from infer.modules.vc.utils import *
+
+
+class VC:
+    def __init__(self, config):
+        self.n_spk = None
+        self.tgt_sr = None
+        self.net_g = None
+        self.pipeline = None
+        self.cpt = None
+        self.version = None
+        self.if_f0 = None
+        self.version = None
+        self.hubert_model = None
+
+        self.config = config
+
+    def get_vc(self, sid, *to_return_protect):
+        logger.info("Get sid: " + sid)
+
+        to_return_protect0 = {
+            "visible": self.if_f0 != 0,
+            "value": (
+                to_return_protect[0] if self.if_f0 != 0 and to_return_protect else 0.5
+            ),
+            "__type__": "update",
+        }
+        to_return_protect1 = {
+            "visible": self.if_f0 != 0,
+            "value": (
+                to_return_protect[1] if self.if_f0 != 0 and to_return_protect else 0.33
+            ),
+            "__type__": "update",
+        }
+
+        if sid == "" or sid == []:
+            if (
+                self.hubert_model is not None
+            ):  # 考虑到轮询, 需要加个判断看是否 sid 是由有模型切换到无模型的
+                logger.info("Clean model cache")
+                del (self.net_g, self.n_spk, self.hubert_model, self.tgt_sr)  # ,cpt
+                self.hubert_model = self.net_g = self.n_spk = self.hubert_model = (
+                    self.tgt_sr
+                ) = None
+                if torch.cuda.is_available():
+                    torch.cuda.empty_cache()
+                ###楼下不这么折腾清理不干净
+                self.if_f0 = self.cpt.get("f0", 1)
+                self.version = self.cpt.get("version", "v1")
+                if self.version == "v1":
+                    if self.if_f0 == 1:
+                        self.net_g = SynthesizerTrnMs256NSFsid(
+                            *self.cpt["config"], is_half=self.config.is_half
+                        )
+                    else:
+                        self.net_g = SynthesizerTrnMs256NSFsid_nono(*self.cpt["config"])
+                elif self.version == "v2":
+                    if self.if_f0 == 1:
+                        self.net_g = SynthesizerTrnMs768NSFsid(
+                            *self.cpt["config"], is_half=self.config.is_half
+                        )
+                    else:
+                        self.net_g = SynthesizerTrnMs768NSFsid_nono(*self.cpt["config"])
+                del self.net_g, self.cpt
+                if torch.cuda.is_available():
+                    torch.cuda.empty_cache()
+            return (
+                {"visible": False, "__type__": "update"},
+                {
+                    "visible": True,
+                    "value": to_return_protect0,
+                    "__type__": "update",
+                },
+                {
+                    "visible": True,
+                    "value": to_return_protect1,
+                    "__type__": "update",
+                },
+                "",
+                "",
+            )
+        person = f'{os.getenv("weight_root")}/{sid}'
+        logger.info(f"Loading: {person}")
+
+        self.cpt = torch.load(person, map_location="cpu")
+        self.tgt_sr = self.cpt["config"][-1]
+        self.cpt["config"][-3] = self.cpt["weight"]["emb_g.weight"].shape[0]  # n_spk
+        self.if_f0 = self.cpt.get("f0", 1)
+        self.version = self.cpt.get("version", "v1")
+
+        synthesizer_class = {
+            ("v1", 1): SynthesizerTrnMs256NSFsid,
+            ("v1", 0): SynthesizerTrnMs256NSFsid_nono,
+            ("v2", 1): SynthesizerTrnMs768NSFsid,
+            ("v2", 0): SynthesizerTrnMs768NSFsid_nono,
+        }
+
+        self.net_g = synthesizer_class.get(
+            (self.version, self.if_f0), SynthesizerTrnMs256NSFsid
+        )(*self.cpt["config"], is_half=self.config.is_half)
+
+        del self.net_g.enc_q
+
+        self.net_g.load_state_dict(self.cpt["weight"], strict=False)
+        self.net_g.eval().to(self.config.device)
+        if self.config.is_half:
+            self.net_g = self.net_g.half()
+        else:
+            self.net_g = self.net_g.float()
+
+        self.pipeline = Pipeline(self.tgt_sr, self.config)
+        n_spk = self.cpt["config"][-3]
+        index = {"value": get_index_path_from_model(sid), "__type__": "update"}
+        logger.info("Select index: " + index["value"])
+
+        return (
+            (
+                {"visible": True, "maximum": n_spk, "__type__": "update"},
+                to_return_protect0,
+                to_return_protect1,
+                index,
+                index,
+            )
+            if to_return_protect
+            else {"visible": True, "maximum": n_spk, "__type__": "update"}
+        )
+
+    def vc_single(
+        self,
+        sid,
+        input_audio_path,
+        f0_up_key,
+        f0_file,
+        f0_method,
+        file_index,
+        file_index2,
+        index_rate,
+        filter_radius,
+        resample_sr,
+        rms_mix_rate,
+        protect,
+    ):
+        if input_audio_path is None:
+            return "You need to upload an audio", None
+        f0_up_key = int(f0_up_key)
+        try:
+            audio = load_audio(input_audio_path, 16000)
+            audio_max = np.abs(audio).max() / 0.95
+            if audio_max > 1:
+                audio /= audio_max
+            times = [0, 0, 0]
+
+            if self.hubert_model is None:
+                self.hubert_model = load_hubert(self.config)
+
+            if file_index:
+                file_index = (
+                    file_index.strip(" ")
+                    .strip('"')
+                    .strip("\n")
+                    .strip('"')
+                    .strip(" ")
+                    .replace("trained", "added")
+                )
+            elif file_index2:
+                file_index = file_index2
+            else:
+                file_index = ""  # 防止小白写错，自动帮他替换掉
+
+            audio_opt = self.pipeline.pipeline(
+                self.hubert_model,
+                self.net_g,
+                sid,
+                audio,
+                input_audio_path,
+                times,
+                f0_up_key,
+                f0_method,
+                file_index,
+                index_rate,
+                self.if_f0,
+                filter_radius,
+                self.tgt_sr,
+                resample_sr,
+                rms_mix_rate,
+                self.version,
+                protect,
+                f0_file,
+            )
+            if self.tgt_sr != resample_sr >= 16000:
+                tgt_sr = resample_sr
+            else:
+                tgt_sr = self.tgt_sr
+            index_info = (
+                "Index:\n%s." % file_index
+                if os.path.exists(file_index)
+                else "Index not used."
+            )
+            return (
+                "Success.\n%s\nTime:\nnpy: %.2fs, f0: %.2fs, infer: %.2fs."
+                % (index_info, *times),
+                (tgt_sr, audio_opt),
+            )
+        except:
+            info = traceback.format_exc()
+            logger.warning(info)
+            return info, (None, None)
+
+    def vc_multi(
+        self,
+        sid,
+        dir_path,
+        opt_root,
+        paths,
+        f0_up_key,
+        f0_method,
+        file_index,
+        file_index2,
+        index_rate,
+        filter_radius,
+        resample_sr,
+        rms_mix_rate,
+        protect,
+        format1,
+    ):
+        try:
+            dir_path = (
+                dir_path.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
+            )  # 防止小白拷路径头尾带了空格和"和回车
+            opt_root = opt_root.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
+            os.makedirs(opt_root, exist_ok=True)
+            try:
+                if dir_path != "":
+                    paths = [
+                        os.path.join(dir_path, name) for name in os.listdir(dir_path)
+                    ]
+                else:
+                    paths = [path.name for path in paths]
+            except:
+                traceback.print_exc()
+                paths = [path.name for path in paths]
+            infos = []
+            for path in paths:
+                info, opt = self.vc_single(
+                    sid,
+                    path,
+                    f0_up_key,
+                    None,
+                    f0_method,
+                    file_index,
+                    file_index2,
+                    # file_big_npy,
+                    index_rate,
+                    filter_radius,
+                    resample_sr,
+                    rms_mix_rate,
+                    protect,
+                )
+                if "Success" in info:
+                    try:
+                        tgt_sr, audio_opt = opt
+                        if format1 in ["wav", "flac"]:
+                            sf.write(
+                                "%s/%s.%s"
+                                % (opt_root, os.path.basename(path), format1),
+                                audio_opt,
+                                tgt_sr,
+                            )
+                        else:
+                            path = "%s/%s.%s" % (
+                                opt_root,
+                                os.path.basename(path),
+                                format1,
+                            )
+                            with BytesIO() as wavf:
+                                sf.write(wavf, audio_opt, tgt_sr, format="wav")
+                                wavf.seek(0, 0)
+                                with open(path, "wb") as outf:
+                                    wav2(wavf, outf, format1)
+                    except:
+                        info += traceback.format_exc()
+                infos.append("%s->%s" % (os.path.basename(path), info))
+                yield "\n".join(infos)
+            yield "\n".join(infos)
+        except:
+            yield traceback.format_exc()

pipeline.py

@@ -0,0 +1,457 @@
+import os
+import sys
+import traceback
+import logging
+
+logger = logging.getLogger(__name__)
+
+from functools import lru_cache
+from time import time as ttime
+
+import faiss
+import librosa
+import numpy as np
+import parselmouth
+import pyworld
+import torch
+import torch.nn.functional as F
+import torchcrepe
+from scipy import signal
+
+now_dir = os.getcwd()
+sys.path.append(now_dir)
+
+bh, ah = signal.butter(N=5, Wn=48, btype="high", fs=16000)
+
+input_audio_path2wav = {}
+
+
+@lru_cache
+def cache_harvest_f0(input_audio_path, fs, f0max, f0min, frame_period):
+    audio = input_audio_path2wav[input_audio_path]
+    f0, t = pyworld.harvest(
+        audio,
+        fs=fs,
+        f0_ceil=f0max,
+        f0_floor=f0min,
+        frame_period=frame_period,
+    )
+    f0 = pyworld.stonemask(audio, f0, t, fs)
+    return f0
+
+
+def change_rms(data1, sr1, data2, sr2, rate):  # 1是输入音频，2是输出音频,rate是2的占比
+    # print(data1.max(),data2.max())
+    rms1 = librosa.feature.rms(
+        y=data1, frame_length=sr1 // 2 * 2, hop_length=sr1 // 2
+    )  # 每半秒一个点
+    rms2 = librosa.feature.rms(y=data2, frame_length=sr2 // 2 * 2, hop_length=sr2 // 2)
+    rms1 = torch.from_numpy(rms1)
+    rms1 = F.interpolate(
+        rms1.unsqueeze(0), size=data2.shape[0], mode="linear"
+    ).squeeze()
+    rms2 = torch.from_numpy(rms2)
+    rms2 = F.interpolate(
+        rms2.unsqueeze(0), size=data2.shape[0], mode="linear"
+    ).squeeze()
+    rms2 = torch.max(rms2, torch.zeros_like(rms2) + 1e-6)
+    data2 *= (
+        torch.pow(rms1, torch.tensor(1 - rate))
+        * torch.pow(rms2, torch.tensor(rate - 1))
+    ).numpy()
+    return data2
+
+
+class Pipeline(object):
+    def __init__(self, tgt_sr, config):
+        self.x_pad, self.x_query, self.x_center, self.x_max, self.is_half = (
+            config.x_pad,
+            config.x_query,
+            config.x_center,
+            config.x_max,
+            config.is_half,
+        )
+        self.sr = 16000  # hubert输入采样率
+        self.window = 160  # 每帧点数
+        self.t_pad = self.sr * self.x_pad  # 每条前后pad时间
+        self.t_pad_tgt = tgt_sr * self.x_pad
+        self.t_pad2 = self.t_pad * 2
+        self.t_query = self.sr * self.x_query  # 查询切点前后查询时间
+        self.t_center = self.sr * self.x_center  # 查询切点位置
+        self.t_max = self.sr * self.x_max  # 免查询时长阈值
+        self.device = config.device
+
+    def get_f0(
+        self,
+        input_audio_path,
+        x,
+        p_len,
+        f0_up_key,
+        f0_method,
+        filter_radius,
+        inp_f0=None,
+    ):
+        global input_audio_path2wav
+        time_step = self.window / self.sr * 1000
+        f0_min = 50
+        f0_max = 1100
+        f0_mel_min = 1127 * np.log(1 + f0_min / 700)
+        f0_mel_max = 1127 * np.log(1 + f0_max / 700)
+        if f0_method == "pm":
+            f0 = (
+                parselmouth.Sound(x, self.sr)
+                .to_pitch_ac(
+                    time_step=time_step / 1000,
+                    voicing_threshold=0.6,
+                    pitch_floor=f0_min,
+                    pitch_ceiling=f0_max,
+                )
+                .selected_array["frequency"]
+            )
+            pad_size = (p_len - len(f0) + 1) // 2
+            if pad_size > 0 or p_len - len(f0) - pad_size > 0:
+                f0 = np.pad(
+                    f0, [[pad_size, p_len - len(f0) - pad_size]], mode="constant"
+                )
+        elif f0_method == "harvest":
+            input_audio_path2wav[input_audio_path] = x.astype(np.double)
+            f0 = cache_harvest_f0(input_audio_path, self.sr, f0_max, f0_min, 10)
+            if filter_radius > 2:
+                f0 = signal.medfilt(f0, 3)
+        elif f0_method == "crepe":
+            model = "full"
+            # Pick a batch size that doesn't cause memory errors on your gpu
+            batch_size = 512
+            # Compute pitch using first gpu
+            audio = torch.tensor(np.copy(x))[None].float()
+            f0, pd = torchcrepe.predict(
+                audio,
+                self.sr,
+                self.window,
+                f0_min,
+                f0_max,
+                model,
+                batch_size=batch_size,
+                device=self.device,
+                return_periodicity=True,
+            )
+            pd = torchcrepe.filter.median(pd, 3)
+            f0 = torchcrepe.filter.mean(f0, 3)
+            f0[pd < 0.1] = 0
+            f0 = f0[0].cpu().numpy()
+        elif f0_method == "rmvpe":
+            if not hasattr(self, "model_rmvpe"):
+                from infer.lib.rmvpe import RMVPE
+
+                logger.info(
+                    "Loading rmvpe model,%s" % "%s/rmvpe.pt" % os.environ["rmvpe_root"]
+                )
+                self.model_rmvpe = RMVPE(
+                    "%s/rmvpe.pt" % os.environ["rmvpe_root"],
+                    is_half=self.is_half,
+                    device=self.device,
+                )
+            f0 = self.model_rmvpe.infer_from_audio(x, thred=0.03)
+
+            if "privateuseone" in str(self.device):  # clean ortruntime memory
+                del self.model_rmvpe.model
+                del self.model_rmvpe
+                logger.info("Cleaning ortruntime memory")
+
+        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
+        if inp_f0 is not None:
+            delta_t = np.round(
+                (inp_f0[:, 0].max() - inp_f0[:, 0].min()) * tf0 + 1
+            ).astype("int16")
+            replace_f0 = np.interp(
+                list(range(delta_t)), inp_f0[:, 0] * 100, inp_f0[:, 1]
+            )
+            shape = f0[self.x_pad * tf0 : self.x_pad * tf0 + len(replace_f0)].shape[0]
+            f0[self.x_pad * tf0 : self.x_pad * tf0 + len(replace_f0)] = replace_f0[
+                :shape
+            ]
+        # with open("test_opt.txt","w")as f:f.write("\n".join([str(i)for i in f0.tolist()]))
+        f0bak = f0.copy()
+        f0_mel = 1127 * np.log(1 + f0 / 700)
+        f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - f0_mel_min) * 254 / (
+            f0_mel_max - 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  # 1-0
+
+    def vc(
+        self,
+        model,
+        net_g,
+        sid,
+        audio0,
+        pitch,
+        pitchf,
+        times,
+        index,
+        big_npy,
+        index_rate,
+        version,
+        protect,
+    ):  # ,file_index,file_big_npy
+        feats = torch.from_numpy(audio0)
+        if self.is_half:
+            feats = feats.half()
+        else:
+            feats = feats.float()
+        if feats.dim() == 2:  # double channels
+            feats = feats.mean(-1)
+        assert feats.dim() == 1, feats.dim()
+        feats = feats.view(1, -1)
+        padding_mask = torch.BoolTensor(feats.shape).to(self.device).fill_(False)
+
+        inputs = {
+            "source": feats.to(self.device),
+            "padding_mask": padding_mask,
+            "output_layer": 9 if version == "v1" else 12,
+        }
+        t0 = ttime()
+        with torch.no_grad():
+            logits = model.extract_features(**inputs)
+            feats = model.final_proj(logits[0]) if version == "v1" else logits[0]
+        if protect < 0.5 and pitch is not None and pitchf is not None:
+            feats0 = feats.clone()
+        if (
+            not isinstance(index, type(None))
+            and not isinstance(big_npy, type(None))
+            and index_rate != 0
+        ):
+            npy = feats[0].cpu().numpy()
+            if self.is_half:
+                npy = npy.astype("float32")
+
+            # _, I = index.search(npy, 1)
+            # npy = big_npy[I.squeeze()]
+
+            score, ix = index.search(npy, k=8)
+            weight = np.square(1 / score)
+            weight /= weight.sum(axis=1, keepdims=True)
+            npy = np.sum(big_npy[ix] * np.expand_dims(weight, axis=2), axis=1)
+
+            if self.is_half:
+                npy = npy.astype("float16")
+            feats = (
+                torch.from_numpy(npy).unsqueeze(0).to(self.device) * index_rate
+                + (1 - index_rate) * feats
+            )
+
+        feats = F.interpolate(feats.permute(0, 2, 1), scale_factor=2).permute(0, 2, 1)
+        if protect < 0.5 and pitch is not None and pitchf is not None:
+            feats0 = F.interpolate(feats0.permute(0, 2, 1), scale_factor=2).permute(
+                0, 2, 1
+            )
+        t1 = ttime()
+        p_len = audio0.shape[0] // self.window
+        if feats.shape[1] < p_len:
+            p_len = feats.shape[1]
+            if pitch is not None and pitchf is not None:
+                pitch = pitch[:, :p_len]
+                pitchf = pitchf[:, :p_len]
+
+        if protect < 0.5 and pitch is not None and pitchf is not None:
+            pitchff = pitchf.clone()
+            pitchff[pitchf > 0] = 1
+            pitchff[pitchf < 1] = protect
+            pitchff = pitchff.unsqueeze(-1)
+            feats = feats * pitchff + feats0 * (1 - pitchff)
+            feats = feats.to(feats0.dtype)
+        p_len = torch.tensor([p_len], device=self.device).long()
+        with torch.no_grad():
+            hasp = pitch is not None and pitchf is not None
+            arg = (feats, p_len, pitch, pitchf, sid) if hasp else (feats, p_len, sid)
+            audio1 = (net_g.infer(*arg)[0][0, 0]).data.cpu().float().numpy()
+            del hasp, arg
+        del feats, p_len, padding_mask
+        if torch.cuda.is_available():
+            torch.cuda.empty_cache()
+        t2 = ttime()
+        times[0] += t1 - t0
+        times[2] += t2 - t1
+        return audio1
+
+    def pipeline(
+        self,
+        model,
+        net_g,
+        sid,
+        audio,
+        input_audio_path,
+        times,
+        f0_up_key,
+        f0_method,
+        file_index,
+        index_rate,
+        if_f0,
+        filter_radius,
+        tgt_sr,
+        resample_sr,
+        rms_mix_rate,
+        version,
+        protect,
+        f0_file=None,
+    ):
+        if (
+            file_index != ""
+            # and file_big_npy != ""
+            # and os.path.exists(file_big_npy) == True
+            and os.path.exists(file_index)
+            and index_rate != 0
+        ):
+            try:
+                index = faiss.read_index(file_index)
+                # big_npy = np.load(file_big_npy)
+                big_npy = index.reconstruct_n(0, index.ntotal)
+            except:
+                traceback.print_exc()
+                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:
+            audio_sum = np.zeros_like(audio)
+            for i in range(self.window):
+                audio_sum += np.abs(audio_pad[i : i - self.window])
+            for t in range(self.t_center, audio.shape[0], self.t_center):
+                opt_ts.append(
+                    t
+                    - self.t_query
+                    + np.where(
+                        audio_sum[t - self.t_query : t + self.t_query]
+                        == audio_sum[t - self.t_query : t + self.t_query].min()
+                    )[0][0]
+                )
+        s = 0
+        audio_opt = []
+        t = None
+        t1 = ttime()
+        audio_pad = np.pad(audio, (self.t_pad, self.t_pad), mode="reflect")
+        p_len = audio_pad.shape[0] // self.window
+        inp_f0 = None
+        if hasattr(f0_file, "name"):
+            try:
+                with open(f0_file.name, "r") as f:
+                    lines = f.read().strip("\n").split("\n")
+                inp_f0 = []
+                for line in lines:
+                    inp_f0.append([float(i) for i in line.split(",")])
+                inp_f0 = np.array(inp_f0, dtype="float32")
+            except:
+                traceback.print_exc()
+        sid = torch.tensor(sid, device=self.device).unsqueeze(0).long()
+        pitch, pitchf = None, None
+        if if_f0 == 1:
+            pitch, pitchf = self.get_f0(
+                input_audio_path,
+                audio_pad,
+                p_len,
+                f0_up_key,
+                f0_method,
+                filter_radius,
+                inp_f0,
+            )
+            pitch = pitch[:p_len]
+            pitchf = pitchf[:p_len]
+            if "mps" not in str(self.device) or "xpu" not in str(self.device):
+                pitchf = pitchf.astype(np.float32)
+            pitch = torch.tensor(pitch, device=self.device).unsqueeze(0).long()
+            pitchf = torch.tensor(pitchf, device=self.device).unsqueeze(0).float()
+        t2 = ttime()
+        times[1] += t2 - t1
+        for t in opt_ts:
+            t = t // self.window * self.window
+            if if_f0 == 1:
+                audio_opt.append(
+                    self.vc(
+                        model,
+                        net_g,
+                        sid,
+                        audio_pad[s : t + self.t_pad2 + self.window],
+                        pitch[:, s // self.window : (t + self.t_pad2) // self.window],
+                        pitchf[:, s // self.window : (t + self.t_pad2) // self.window],
+                        times,
+                        index,
+                        big_npy,
+                        index_rate,
+                        version,
+                        protect,
+                    )[self.t_pad_tgt : -self.t_pad_tgt]
+                )
+            else:
+                audio_opt.append(
+                    self.vc(
+                        model,
+                        net_g,
+                        sid,
+                        audio_pad[s : t + self.t_pad2 + self.window],
+                        None,
+                        None,
+                        times,
+                        index,
+                        big_npy,
+                        index_rate,
+                        version,
+                        protect,
+                    )[self.t_pad_tgt : -self.t_pad_tgt]
+                )
+            s = t
+        if if_f0 == 1:
+            audio_opt.append(
+                self.vc(
+                    model,
+                    net_g,
+                    sid,
+                    audio_pad[t:],
+                    pitch[:, t // self.window :] if t is not None else pitch,
+                    pitchf[:, t // self.window :] if t is not None else pitchf,
+                    times,
+                    index,
+                    big_npy,
+                    index_rate,
+                    version,
+                    protect,
+                )[self.t_pad_tgt : -self.t_pad_tgt]
+            )
+        else:
+            audio_opt.append(
+                self.vc(
+                    model,
+                    net_g,
+                    sid,
+                    audio_pad[t:],
+                    None,
+                    None,
+                    times,
+                    index,
+                    big_npy,
+                    index_rate,
+                    version,
+                    protect,
+                )[self.t_pad_tgt : -self.t_pad_tgt]
+            )
+        audio_opt = np.concatenate(audio_opt)
+        if rms_mix_rate != 1:
+            audio_opt = change_rms(audio, 16000, audio_opt, tgt_sr, rms_mix_rate)
+        if tgt_sr != resample_sr >= 16000:
+            audio_opt = librosa.resample(
+                audio_opt, orig_sr=tgt_sr, target_sr=resample_sr
+            )
+        audio_max = np.abs(audio_opt).max() / 0.99
+        max_int16 = 32768
+        if audio_max > 1:
+            max_int16 /= audio_max
+        audio_opt = (audio_opt * max_int16).astype(np.int16)
+        del pitch, pitchf, sid
+        if torch.cuda.is_available():
+            torch.cuda.empty_cache()
+        return audio_opt

pyproject.toml

@@ -0,0 +1,64 @@
+[tool.poetry]
+name = "rvc-beta"
+version = "0.1.0"
+description = ""
+authors = ["lj1995"]
+license = "MIT"
+
+[tool.poetry.dependencies]
+python = "^3.9"
+torch = "2.4.0"
+torchaudio = "2.4.0"
+Cython = "^3.0.11"
+gradio = "3.34.0"
+pydub = ">=0.25.1"
+soundfile = ">=0.12.1"
+ffmpeg-python = ">=0.2.0"
+tensorboardX = "^2.6.2.2"
+fairseq = "0.12.2"
+faiss-cpu = "1.7.3"
+Jinja2 = ">=3.1.2"
+json5 = "^0.9.25"
+librosa = "0.9.1"
+llvmlite = "0.39.0"
+Markdown = "^3.6"
+matplotlib = ">=3.7.0"
+matplotlib-inline = ">=0.1.3"
+numba = "0.56.4"
+numpy = "1.23.5"
+scipy = "1.13.1"
+praat-parselmouth = ">=0.4.2"
+Pillow = ">=9.1.1"
+pyworld = "0.3.2"
+resampy = ">=0.4.2"
+scikit-learn = "^1.5.1"
+tensorboard = "^2.17.0"
+tqdm = ">=4.63.1"
+tornado = ">=6.1"
+Werkzeug = ">=2.2.3"
+uc-micro-py = ">=1.0.1"
+sympy = ">=1.11.1"
+tabulate = ">=0.8.10"
+PyYAML = ">=6.0"
+pyasn1 = ">=0.4.8"
+pyasn1-modules = ">=0.2.8"
+fsspec = ">=2022.11.0"
+absl-py = ">=1.2.0"
+audioread = "^3.0.1"
+uvicorn = ">=0.21.1"
+colorama = ">=0.4.5"
+torchcrepe = "0.0.20"
+python-dotenv = ">=1.0.0"
+av = "^12.3.0"
+joblib = ">=1.1.0"
+httpx = "^0.27.0"
+onnxruntime-gpu = "^1.18.1"
+fastapi = "0.88"
+torchfcpe = "^0.0.4"
+ffmpy = "0.3.1"
+torchvision = "0.19.0"
+[tool.poetry.dev-dependencies]
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"

requirements.txt

@@ -0,0 +1,34 @@
+aria2
+joblib>=1.1.0
+numba==0.56.4
+numpy==1.23.5
+scipy
+librosa==0.9.1
+llvmlite==0.39.0
+fairseq==0.12.2
+faiss-cpu==1.7.3
+gradio==3.34.0
+Cython
+pydub>=0.25.1
+soundfile>=0.12.1
+ffmpeg-python>=0.2.0
+tensorboardX
+Jinja2>=3.1.2
+json5
+Markdown
+matplotlib>=3.7.0
+matplotlib-inline>=0.1.3
+praat-parselmouth>=0.4.2
+
+tensorboard
+tqdm>=4.63.1
+tornado>=6.1
+httpx
+onnxruntime; sys_platform == 'darwin'
+onnxruntime-gpu; sys_platform != 'darwin'
+torchcrepe==0.0.20
+fastapi==0.88
+torchfcpe
+ffmpy==0.3.1
+python-dotenv>=1.0.0
+av

utils.py

@@ -0,0 +1,33 @@
+import os
+
+from fairseq import checkpoint_utils
+
+
+def get_index_path_from_model(sid):
+    return next(
+        (
+            f
+            for f in [
+                os.path.join(root, name)
+                for root, _, files in os.walk(os.getenv("index_root"), topdown=False)
+                for name in files
+                if name.endswith(".index") and "trained" not in name
+            ]
+            if sid.split(".")[0] in f
+        ),
+        "",
+    )
+
+
+def load_hubert(config):
+    models, _, _ = checkpoint_utils.load_model_ensemble_and_task(
+        ["assets/hubert/hubert_base.pt"],
+        suffix="",
+    )
+    hubert_model = models[0]
+    hubert_model = hubert_model.to(config.device)
+    if config.is_half:
+        hubert_model = hubert_model.half()
+    else:
+        hubert_model = hubert_model.float()
+    return hubert_model.eval()