run.py

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

sup_audioext = {
    "wav",
    "mp3",
    "flac",
    "ogg",
    "opus",
    "m4a",
    "mp4",
    "aac",
    "alac",
    "wma",
    "aiff",
    "webm",
    "ac3",
}

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",
                "SUPER"
            ]
        ):
            # 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")

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))
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 change_choices2():
    audio_files=[]
    for filename in os.listdir("./audios"):
        if filename.endswith(('.wav','.mp3','.flac','.m4a','.ogg')):
            audio_files.append(os.path.join('./audios',filename))
    return {"choices": sorted(audio_files), "__type__": "update"}

def save_to_wav2(dropbox):
    file_path=dropbox.name
    shutil.move(file_path,'./audios')
    return os.path.join('./audios',os.path.basename(file_path))

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,dataset_path],[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, dataset_path, 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,
    dataset_path,
    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(dataset_path, 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"}

datasets_path = os.path.join(now_dir, "assets", "datasets")

if not os.path.exists(datasets_path):
    os.makedirs(datasets_path)

datasets_path_relative = os.path.relpath(datasets_path, now_dir)

def get_datasets_list():
    return [
        dirpath
        for dirpath, _, filenames in os.walk(datasets_path_relative)
        if any(filename.endswith(tuple(sup_audioext)) for filename in filenames)
    ]


def refresh_datasets():
    return {"choices": sorted(get_datasets_list()), "__type__": "update"}


with gr.Blocks(theme='gradio/base', title="Kanoyo") as app:
    gr.HTML('''
        <h1 style="display: flex; align-items: center;">
            <img src="https://art.pixilart.com/sr220411b1340ff.png" alt="heart" style="width:42px;height:42px;border-radius:10%;margin-right:10px;">
            Kanoyo WebUI
        </h1>
    ''')
    gr.HTML(
        "<h3>Лучший Telegram-канал во всей вселенной — <a href='https://t.me/kanoyotelegram'>Присоединяйся!</a></h3>"
    )
    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),
                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,
                )
                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,
                )
                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")
                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,
                            )
                            dropbox = gr.File(label="Drop your audio here & hit the Reload button.")
                            input_audio0 = gr.Dropdown(
                            label=i18n("Choose Your Audio"),
                            value=i18n("audios/someguy.mp3")
                            )
                            refresh_button2 = gr.Button("Обновить", variant="primary", size='sm')
                            refresh_button2.click(fn=change_choices2, inputs=[], outputs=[input_audio0])

                            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,
                            )
                            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,
                            )
                            dropbox.upload(fn=save_to_wav2, inputs=[dropbox], outputs=[input_audio0])
                            dropbox.upload(fn=change_choices2, inputs=[], outputs=[input_audio0])

                        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("训练")):
            with gr.Row():
                exp_dir1 = gr.Textbox(label=i18n("输入实验名"), value="model-name")
                sr2 = gr.Radio(
                    label=i18n("目标采样率"),
                    choices=["40k"],
                    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=["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
                with gr.Row():
                    dataset_path = gr.Dropdown(
                        label=i18n("Dataset Path"),
                        info=i18n("Path to the dataset folder."),
                        # placeholder=i18n("Enter dataset path"),
                        choices=get_datasets_list(),
                        allow_custom_value=True,
                        interactive=True,
                    )
                    refresh_datasets_button = gr.Button(i18n("DATASET_REFRESH"))
                    spk_id5 = gr.Slider(
                        minimum=0,
                        maximum=4,
                        step=1,
                        label=i18n("请指定说话人id"),
                        value=0,
                        interactive=True,
                    )
                    refresh_datasets_button.click(
                        fn=refresh_datasets,
                        inputs=[],
                        outputs=[dataset_path],
                    )
                    but1 = gr.Button(i18n("处理数据"), variant="primary")
                    info1 = gr.Textbox(label=i18n("输出信息"), value="")
                    but1.click(
                        preprocess_dataset,
                        [dataset_path, exp_dir1, sr2, np7],
                        [info1],
                        api_name="train_preprocess",
                    )
            with gr.Group():
                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():
                with gr.Row():
                    save_epoch10 = gr.Slider(
                        minimum=1,
                        maximum=500,
                        step=1,
                        label=i18n("保存频率save_every_epoch"),
                        value=5,
                        interactive=True,
                    )
                    total_epoch11 = gr.Slider(
                        minimum=1,
                        maximum=22222,
                        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("是"),
                        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("是"),
                        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/G_SnowieV3.1_40k.pth",
                        interactive=True,
                    )
                    pretrained_D15 = gr.Textbox(
                        label=i18n("加载预训练底模D路径"),
                        value="assets/pretrained_v2/D_SnowieV3.1_40k.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,
                            dataset_path,
                            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",
                    )

    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,
            share=False,
            quiet=True,
        )