docker/Retrieval-based-Voice-Conversion-WebUI/infer.py

from multiprocessing import cpu_count
import threading
from time import sleep
from subprocess import Popen
from time import sleep
import torch, os, traceback, sys, warnings, shutil, numpy as np
import faiss

now_dir = os.getcwd()
sys.path.append(now_dir)
tmp = os.path.join(now_dir, "TEMP")
shutil.rmtree(tmp, 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, "weights"), exist_ok=True)
os.environ["TEMP"] = tmp
warnings.filterwarnings("ignore")
torch.manual_seed(114514)
from i18n import I18nAuto

i18n = I18nAuto()
# 判断是否有能用来训练和加速推理的N卡
ncpu = cpu_count()
ngpu = torch.cuda.device_count()
gpu_infos = []
if (not torch.cuda.is_available()) or ngpu == 0:
    if_gpu_ok = False
else:
    if_gpu_ok = False
    for i in range(ngpu):
        gpu_name = torch.cuda.get_device_name(i)
        if ("16" in gpu_name and "V100" not in gpu_name) or "MX" in gpu_name:
            continue
        if (
            "10" in gpu_name
            or "20" in gpu_name
            or "30" in gpu_name
            or "40" in gpu_name
            or "A2" in gpu_name.upper()
            or "A3" in gpu_name.upper()
            or "A4" in gpu_name.upper()
            or "P4" in gpu_name.upper()
            or "A50" in gpu_name.upper()
            or "70" in gpu_name
            or "80" in gpu_name
            or "90" in gpu_name
            or "M4" in gpu_name
            or "T4" in gpu_name
            or "TITAN" in gpu_name.upper()
        ):  # A10#A100#V100#A40#P40#M40#K80
            if_gpu_ok = True  # 至少有一张能用的N卡
            gpu_infos.append("%s\t%s" % (i, gpu_name))
gpu_info = (
    "\n".join(gpu_infos)
    if if_gpu_ok == True and len(gpu_infos) > 0
    else "很遗憾您这没有能用的显卡来支持您训练"
)
gpus = "-".join([i[0] for i in gpu_infos])
from infer_pack.models import SynthesizerTrnMs256NSFsid, SynthesizerTrnMs256NSFsid_nono
from scipy.io import wavfile
from fairseq import checkpoint_utils
import gradio as gr
import logging
from vc_infer_pipeline import VC
from config import (
    is_half,
    device,
    python_cmd,
    listen_port,
    iscolab,
    noparallel,
    noautoopen,
)
from infer_uvr5 import _audio_pre_
from my_utils import load_audio
from train.process_ckpt import show_info, change_info, merge, extract_small_model

# from trainset_preprocess_pipeline import PreProcess
logging.getLogger("numba").setLevel(logging.WARNING)


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"


hubert_model = None


def load_hubert():
    global hubert_model
    models, _, _ = checkpoint_utils.load_model_ensemble_and_task(
        ["hubert_base.pt"],
        suffix="",
    )
    hubert_model = models[0]
    hubert_model = hubert_model.to(device)
    if is_half:
        hubert_model = hubert_model.half()
    else:
        hubert_model = hubert_model.float()
    hubert_model.eval()


weight_root = "weights"
weight_uvr5_root = "uvr5_weights"
names = []
for name in os.listdir(weight_root):
    if name.endswith(".pth"):
        names.append(name)
uvr5_names = []
for name in os.listdir(weight_uvr5_root):
    if name.endswith(".pth"):
        uvr5_names.append(name.replace(".pth", ""))


def vc_single(
    sid,
    input_audio,
    f0_up_key,
    f0_file,
    f0_method,
    file_index,
    file_big_npy,
    index_rate,
    weights_path,
):  # spk_item, input_audio0, vc_transform0,f0_file,f0method0
    global tgt_sr, net_g, vc, hubert_model
    get_vc("", weights_path)
    if input_audio is None:
        return "You need to upload an audio", None
    f0_up_key = int(f0_up_key)
    try:
        audio = load_audio(input_audio, 16000)
        times = [0, 0, 0]
        if hubert_model == None:
            load_hubert()
        if_f0 = cpt.get("f0", 1)
        file_index = (
            file_index.strip(" ")
            .strip('"')
            .strip("\n")
            .strip('"')
            .strip(" ")
            .replace("trained", "added")
        )  # 防止小白写错，自动帮他替换掉
        file_big_npy = (
            file_big_npy.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
        )
        audio_opt = vc.pipeline(
            hubert_model,
            net_g,
            sid,
            audio,
            times,
            f0_up_key,
            f0_method,
            file_index,
            file_big_npy,
            index_rate,
            if_f0,
            f0_file=f0_file,
        )
        print(
            "npy: ", times[0], "s, f0: ", times[1], "s, infer: ", times[2], "s", sep=""
        )
        return "Success", (tgt_sr, audio_opt)
    except:
        info = traceback.format_exc()
        print(info)
        return info, (None, None)


def vc_multi(
    sid,
    dir_path,
    opt_root,
    paths,
    f0_up_key,
    f0_method,
    file_index,
    file_big_npy,
    index_rate,
):
    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 = vc_single(
                sid,
                path,
                f0_up_key,
                None,
                f0_method,
                file_index,
                file_big_npy,
                index_rate,
            )
            if info == "Success":
                try:
                    tgt_sr, audio_opt = opt
                    wavfile.write(
                        "%s/%s" % (opt_root, os.path.basename(path)), tgt_sr, audio_opt
                    )
                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()


def uvr(model_name, inp_root, save_root_vocal, paths, save_root_ins):
    infos = []
    try:
        inp_root = inp_root.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
        save_root_vocal = (
            save_root_vocal.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
        )
        save_root_ins = (
            save_root_ins.strip(" ").strip('"').strip("\n").strip('"').strip(" ")
        )
        pre_fun = _audio_pre_(
            model_path=os.path.join(weight_uvr5_root, model_name + ".pth"),
            device=device,
            is_half=is_half,
        )
        if inp_root != "":
            paths = [os.path.join(inp_root, name) for name in os.listdir(inp_root)]
        else:
            paths = [path.name for path in paths]
        for name in paths:
            inp_path = os.path.join(inp_root, name)
            try:
                pre_fun._path_audio_(inp_path, save_root_ins, save_root_vocal)
                infos.append("%s->Success" % (os.path.basename(inp_path)))
                yield "\n".join(infos)
            except:
                infos.append(
                    "%s->%s" % (os.path.basename(inp_path), traceback.format_exc())
                )
                yield "\n".join(infos)
    except:
        infos.append(traceback.format_exc())
        yield "\n".join(infos)
    finally:
        try:
            del pre_fun.model
            del pre_fun
        except:
            traceback.print_exc()
        print("clean_empty_cache")
        if torch.cuda.is_available():
            torch.cuda.empty_cache()
    yield "\n".join(infos)


# 一个选项卡全局只能有一个音色
def get_vc(sid, weights_path):
    global n_spk, tgt_sr, net_g, vc, cpt
    if sid == []:
        global hubert_model
        if hubert_model != 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
            print("clean_empty_cache")
            del net_g, n_spk, vc, hubert_model, tgt_sr  # ,cpt
            hubert_model = net_g = n_spk = vc = hubert_model = tgt_sr = None
            if torch.cuda.is_available():
                torch.cuda.empty_cache()
            ###楼下不这么折腾清理不干净
            if_f0 = cpt.get("f0", 1)
            if if_f0 == 1:
                net_g = SynthesizerTrnMs256NSFsid(*cpt["config"], is_half=is_half)
            else:
                net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
            del net_g, cpt
            if torch.cuda.is_available():
                torch.cuda.empty_cache()
            cpt = None
        return {"visible": False, "__type__": "update"}
    person = "%s/%s" % (weight_root, sid)
    print("loading %s" % person)
    cpt = torch.load(weights_path, map_location="cpu")
    tgt_sr = cpt["config"][-1]
    cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0]  # n_spk
    if_f0 = cpt.get("f0", 1)
    if if_f0 == 1:
        net_g = SynthesizerTrnMs256NSFsid(*cpt["config"], is_half=is_half)
    else:
        net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
    del net_g.enc_q
    print(net_g.load_state_dict(cpt["weight"], strict=False))  # 不加这一行清不干净, 真奇葩
    net_g.eval().to(device)
    if is_half:
        net_g = net_g.half()
    else:
        net_g = net_g.float()
    vc = VC(tgt_sr, device, is_half)
    n_spk = cpt["config"][-3]
    return {"visible": True, "maximum": n_spk, "__type__": "update"}


def change_choices():
    names = []
    for name in os.listdir(weight_root):
        if name.endswith(".pth"):
            names.append(name)
    return {"choices": sorted(names), "__type__": "update"}


def clean():
    return {"value": "", "__type__": "update"}


def change_f0(if_f0_3, sr2):  # np7, f0method8,pretrained_G14,pretrained_D15
    if if_f0_3 == "是":
        return (
            {"visible": True, "__type__": "update"},
            {"visible": True, "__type__": "update"},
            "pretrained/f0G%s.pth" % sr2,
            "pretrained/f0D%s.pth" % sr2,
        )
    return (
        {"visible": False, "__type__": "update"},
        {"visible": False, "__type__": "update"},
        "pretrained/G%s.pth" % sr2,
        "pretrained/D%s.pth" % sr2,
    )


sr_dict = {
    "32k": 32000,
    "40k": 40000,
    "48k": 48000,
}


def if_done(done, p):
    while 1:
        if p.poll() == 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() == None:
                flag = 0
                sleep(0.5)
                break
        if flag == 1:
            break
    done[0] = True


def preprocess_dataset(trainset_dir, exp_dir, sr, n_p=ncpu):
    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 = (
        python_cmd
        + " trainset_preprocess_pipeline_print.py %s %s %s %s/logs/%s "
        % (trainset_dir, sr, n_p, now_dir, exp_dir)
        + str(noparallel)
    )
    print(cmd)
    p = Popen(cmd, shell=True)  # , stdin=PIPE, stdout=PIPE,stderr=PIPE,cwd=now_dir
    ###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] == True:
            break
    with open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "r") as f:
        log = f.read()
    print(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):
    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 == "是":
        cmd = python_cmd + " extract_f0_print.py %s/logs/%s %s %s" % (
            now_dir,
            exp_dir,
            n_p,
            f0method,
        )
        print(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()
        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] == True:
                break
        with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
            log = f.read()
        print(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 = python_cmd + " extract_feature_print.py %s %s %s %s %s/logs/%s" % (
            device,
            leng,
            idx,
            n_g,
            now_dir,
            exp_dir,
        )
        print(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] == True:
            break
    with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f:
        log = f.read()
    print(log)
    yield log


def change_sr2(sr2, if_f0_3):
    if if_f0_3 == "是":
        return "pretrained/f0G%s.pth" % sr2, "pretrained/f0D%s.pth" % sr2
    else:
        return "pretrained/G%s.pth" % sr2, "pretrained/D%s.pth" % 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,
):
    # 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)
    co256_dir = "%s/3_feature256" % (exp_dir)
    if if_f0_3 == "是":
        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(co256_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(co256_dir)]
        )
    opt = []
    for name in names:
        if if_f0_3 == "是":
            opt.append(
                "%s/%s.wav|%s/%s.npy|%s/%s.wav.npy|%s/%s.wav.npy|%s"
                % (
                    gt_wavs_dir.replace("\\", "\\\\"),
                    name,
                    co256_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,
                    co256_dir.replace("\\", "\\\\"),
                    name,
                    spk_id5,
                )
            )
    if if_f0_3 == "是":
        opt.append(
            "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature256/mute.npy|%s/logs/mute/2a_f0/mute.wav.npy|%s/logs/mute/2b-f0nsf/mute.wav.npy|%s"
            % (now_dir, sr2, now_dir, now_dir, now_dir, spk_id5)
        )
    else:
        opt.append(
            "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature256/mute.npy|%s"
            % (now_dir, sr2, now_dir, spk_id5)
        )
    with open("%s/filelist.txt" % exp_dir, "w") as f:
        f.write("\n".join(opt))
    print("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"
    print("use gpus:", gpus16)
    if gpus16:
        cmd = (
            python_cmd
            + " train_nsf_sim_cache_sid_load_pretrain.py -e %s -sr %s -f0 %s -bs %s -g %s -te %s -se %s -pg %s -pd %s -l %s -c %s"
            % (
                exp_dir1,
                sr2,
                1 if if_f0_3 == "是" else 0,
                batch_size12,
                gpus16,
                total_epoch11,
                save_epoch10,
                pretrained_G14,
                pretrained_D15,
                1 if if_save_latest13 == "是" else 0,
                1 if if_cache_gpu17 == "是" else 0,
            )
        )
    else:
        cmd = (
            python_cmd
            + " train_nsf_sim_cache_sid_load_pretrain.py -e %s -sr %s -f0 %s -bs %s -te %s -se %s -pg %s -pd %s -l %s -c %s"
            % (
                exp_dir1,
                sr2,
                1 if if_f0_3 == "是" else 0,
                batch_size12,
                total_epoch11,
                save_epoch10,
                pretrained_G14,
                pretrained_D15,
                1 if if_save_latest13 == "是" else 0,
                1 if if_cache_gpu17 == "是" else 0,
            )
        )
    print(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):
    exp_dir = "%s/logs/%s" % (now_dir, exp_dir1)
    os.makedirs(exp_dir, exist_ok=True)
    feature_dir = "%s/3_feature256" % (exp_dir)
    if os.path.exists(feature_dir) == False:
        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！"
    npys = []
    for name in sorted(listdir_res):
        phone = np.load("%s/%s" % (feature_dir, name))
        npys.append(phone)
    big_npy = np.concatenate(npys, 0)
    np.save("%s/total_fea.npy" % exp_dir, big_npy)
    n_ivf = big_npy.shape[0] // 39
    infos = []
    infos.append("%s,%s" % (big_npy.shape, n_ivf))
    yield "\n".join(infos)
    index = faiss.index_factory(256, "IVF%s,Flat" % n_ivf)
    infos.append("training")
    yield "\n".join(infos)
    index_ivf = faiss.extract_index_ivf(index)  #
    index_ivf.nprobe = int(np.power(n_ivf, 0.3))
    index.train(big_npy)
    faiss.write_index(
        index,
        "%s/trained_IVF%s_Flat_nprobe_%s.index" % (exp_dir, n_ivf, index_ivf.nprobe),
    )
    infos.append("adding")
    yield "\n".join(infos)
    index.add(big_npy)
    faiss.write_index(
        index,
        "%s/added_IVF%s_Flat_nprobe_%s.index" % (exp_dir, n_ivf, index_ivf.nprobe),
    )
    infos.append("成功构建索引, added_IVF%s_Flat_nprobe_%s.index" % (n_ivf, index_ivf.nprobe))
    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,
    gpus6,
    np7,
    f0method8,
    save_epoch10,
    total_epoch11,
    batch_size12,
    if_save_latest13,
    pretrained_G14,
    pretrained_D15,
    gpus16,
    if_cache_gpu17,
):
    infos = []

    def get_info_str(strr):
        infos.append(strr)
        return "\n".join(infos)

    os.makedirs("%s/logs/%s" % (now_dir, exp_dir1), exist_ok=True)
    #########step1:处理数据
    open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir1), "w").close()
    cmd = (
        python_cmd
        + " trainset_preprocess_pipeline_print.py %s %s %s %s/logs/%s "
        % (trainset_dir4, sr_dict[sr2], ncpu, now_dir, exp_dir1)
        + str(noparallel)
    )
    yield get_info_str("step1:正在处理数据")
    yield get_info_str(cmd)
    p = Popen(cmd, shell=True)
    p.wait()
    with open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir1), "r") as f:
        print(f.read())
    #########step2a:提取音高
    open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir1), "w")
    if if_f0_3 == "是":
        yield get_info_str("step2a:正在提取音高")
        cmd = python_cmd + " extract_f0_print.py %s/logs/%s %s %s" % (
            now_dir,
            exp_dir1,
            np7,
            f0method8,
        )
        yield get_info_str(cmd)
        p = Popen(cmd, shell=True, cwd=now_dir)
        p.wait()
        with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir1), "r") as f:
            print(f.read())
    else:
        yield get_info_str("step2a:无需提取音高")
    #######step2b:提取特征
    yield get_info_str("step2b:正在提取特征")
    gpus = gpus16.split("-")
    leng = len(gpus)
    ps = []
    for idx, n_g in enumerate(gpus):
        cmd = python_cmd + " extract_feature_print.py %s %s %s %s %s/logs/%s" % (
            device,
            leng,
            idx,
            n_g,
            now_dir,
            exp_dir1,
        )
        yield get_info_str(cmd)
        p = Popen(
            cmd, shell=True, cwd=now_dir
        )  # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir
        ps.append(p)
    for p in ps:
        p.wait()
    with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir1), "r") as f:
        print(f.read())
    #######step3a:训练模型
    yield get_info_str("step3a:正在训练模型")
    # 生成filelist
    exp_dir = "%s/logs/%s" % (now_dir, exp_dir1)
    gt_wavs_dir = "%s/0_gt_wavs" % (exp_dir)
    co256_dir = "%s/3_feature256" % (exp_dir)
    if if_f0_3 == "是":
        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(co256_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(co256_dir)]
        )
    opt = []
    for name in names:
        if if_f0_3 == "是":
            opt.append(
                "%s/%s.wav|%s/%s.npy|%s/%s.wav.npy|%s/%s.wav.npy|%s"
                % (
                    gt_wavs_dir.replace("\\", "\\\\"),
                    name,
                    co256_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,
                    co256_dir.replace("\\", "\\\\"),
                    name,
                    spk_id5,
                )
            )
    if if_f0_3 == "是":
        opt.append(
            "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature256/mute.npy|%s/logs/mute/2a_f0/mute.wav.npy|%s/logs/mute/2b-f0nsf/mute.wav.npy|%s"
            % (now_dir, sr2, now_dir, now_dir, now_dir, spk_id5)
        )
    else:
        opt.append(
            "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature256/mute.npy|%s"
            % (now_dir, sr2, now_dir, spk_id5)
        )
    with open("%s/filelist.txt" % exp_dir, "w") as f:
        f.write("\n".join(opt))
    yield get_info_str("write filelist done")
    if gpus16:
        cmd = (
            python_cmd
            + " train_nsf_sim_cache_sid_load_pretrain.py -e %s -sr %s -f0 %s -bs %s -g %s -te %s -se %s -pg %s -pd %s -l %s -c %s"
            % (
                exp_dir1,
                sr2,
                1 if if_f0_3 == "是" else 0,
                batch_size12,
                gpus16,
                total_epoch11,
                save_epoch10,
                pretrained_G14,
                pretrained_D15,
                1 if if_save_latest13 == "是" else 0,
                1 if if_cache_gpu17 == "是" else 0,
            )
        )
    else:
        cmd = (
            python_cmd
            + " train_nsf_sim_cache_sid_load_pretrain.py -e %s -sr %s -f0 %s -bs %s -te %s -se %s -pg %s -pd %s -l %s -c %s"
            % (
                exp_dir1,
                sr2,
                1 if if_f0_3 == "是" else 0,
                batch_size12,
                total_epoch11,
                save_epoch10,
                pretrained_G14,
                pretrained_D15,
                1 if if_save_latest13 == "是" else 0,
                1 if if_cache_gpu17 == "是" else 0,
            )
        )
    yield get_info_str(cmd)
    p = Popen(cmd, shell=True, cwd=now_dir)
    p.wait()
    yield get_info_str("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
    feature_dir = "%s/3_feature256" % (exp_dir)
    npys = []
    listdir_res = list(os.listdir(feature_dir))
    for name in sorted(listdir_res):
        phone = np.load("%s/%s" % (feature_dir, name))
        npys.append(phone)
    big_npy = np.concatenate(npys, 0)
    np.save("%s/total_fea.npy" % exp_dir, big_npy)
    n_ivf = big_npy.shape[0] // 39
    yield get_info_str("%s,%s" % (big_npy.shape, n_ivf))
    index = faiss.index_factory(256, "IVF%s,Flat" % n_ivf)
    yield get_info_str("training index")
    index_ivf = faiss.extract_index_ivf(index)  #
    index_ivf.nprobe = int(np.power(n_ivf, 0.3))
    index.train(big_npy)
    faiss.write_index(
        index,
        "%s/trained_IVF%s_Flat_nprobe_%s.index" % (exp_dir, n_ivf, index_ivf.nprobe),
    )
    yield get_info_str("adding index")
    index.add(big_npy)
    faiss.write_index(
        index,
        "%s/added_IVF%s_Flat_nprobe_%s.index" % (exp_dir, n_ivf, index_ivf.nprobe),
    )
    yield get_info_str(
        "成功构建索引, added_IVF%s_Flat_nprobe_%s.index" % (n_ivf, index_ivf.nprobe)
    )
    yield get_info_str("全流程结束！")


#                    ckpt_path2.change(change_info_,[ckpt_path2],[sr__,if_f0__])
def change_info_(ckpt_path):
    if (
        os.path.exists(ckpt_path.replace(os.path.basename(ckpt_path), "train.log"))
        == False
    ):
        return {"__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"]
            return sr, str(f0)
    except:
        traceback.print_exc()
        return {"__type__": "update"}, {"__type__": "update"}


from infer_pack.models_onnx_moess import SynthesizerTrnMs256NSFsidM
from infer_pack.models_onnx import SynthesizerTrnMs256NSFsidO


def export_onnx(ModelPath, ExportedPath, MoeVS=True):
    hidden_channels = 256  # hidden_channels，为768Vec做准备
    cpt = torch.load(ModelPath, map_location="cpu")
    cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0]  # n_spk
    print(*cpt["config"])

    test_phone = torch.rand(1, 200, hidden_channels)  # hidden unit
    test_phone_lengths = torch.tensor([200]).long()  # hidden unit 长度（貌似没啥用）
    test_pitch = torch.randint(size=(1, 200), low=5, high=255)  # 基频（单位赫兹）
    test_pitchf = torch.rand(1, 200)  # nsf基频
    test_ds = torch.LongTensor([0])  # 说话人ID
    test_rnd = torch.rand(1, 192, 200)  # 噪声（加入随机因子）

    device = "cpu"  # 导出时设备（不影响使用模型）

    if MoeVS:
        net_g = SynthesizerTrnMs256NSFsidM(
            *cpt["config"], is_half=False
        )  # fp32导出（C++要支持fp16必须手动将内存重新排列所以暂时不用fp16）
        net_g.load_state_dict(cpt["weight"], strict=False)
        input_names = ["phone", "phone_lengths", "pitch", "pitchf", "ds", "rnd"]
        output_names = [
            "audio",
        ]
        torch.onnx.export(
            net_g,
            (
                test_phone.to(device),
                test_phone_lengths.to(device),
                test_pitch.to(device),
                test_pitchf.to(device),
                test_ds.to(device),
                test_rnd.to(device),
            ),
            ExportedPath,
            dynamic_axes={
                "phone": [1],
                "pitch": [1],
                "pitchf": [1],
                "rnd": [2],
            },
            do_constant_folding=False,
            opset_version=16,
            verbose=False,
            input_names=input_names,
            output_names=output_names,
        )
    else:
        net_g = SynthesizerTrnMs256NSFsidO(
            *cpt["config"], is_half=False
        )  # fp32导出（C++要支持fp16必须手动将内存重新排列所以暂时不用fp16）
        net_g.load_state_dict(cpt["weight"], strict=False)
        input_names = ["phone", "phone_lengths", "pitch", "pitchf", "ds"]
        output_names = [
            "audio",
        ]
        torch.onnx.export(
            net_g,
            (
                test_phone.to(device),
                test_phone_lengths.to(device),
                test_pitch.to(device),
                test_pitchf.to(device),
                test_ds.to(device),
            ),
            ExportedPath,
            dynamic_axes={
                "phone": [1],
                "pitch": [1],
                "pitchf": [1],
            },
            do_constant_folding=False,
            opset_version=16,
            verbose=False,
            input_names=input_names,
            output_names=output_names,
        )
    return "Finished"