rvc.py

import subprocess, torch, os, traceback, sys, warnings, shutil, numpy as np
from mega import Mega
os.environ["no_proxy"] = "localhost, 127.0.0.1, ::1"
import threading
from time import sleep
from subprocess import Popen
import faiss
from random import shuffle
import json, datetime, requests
from gtts import gTTS
now_dir = os.getcwd()
sys.path.append(now_dir)
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)
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

import signal

import math

from utils import load_audio, CSVutil

global DoFormant, Quefrency, Timbre

if not os.path.isdir('csvdb/'):
    os.makedirs('csvdb')
    frmnt, stp = open("csvdb/formanting.csv", 'w'), open("csvdb/stop.csv", 'w')
    frmnt.close()
    stp.close()

try:
    DoFormant, Quefrency, Timbre = CSVutil('csvdb/formanting.csv', 'r', 'formanting')
    DoFormant = (
        lambda DoFormant: True if DoFormant.lower() == 'true' else (False if DoFormant.lower() == 'false' else DoFormant)
    )(DoFormant)
except (ValueError, TypeError, IndexError):
    DoFormant, Quefrency, Timbre = False, 1.0, 1.0
    CSVutil('csvdb/formanting.csv', 'w+', 'formanting', DoFormant, Quefrency, Timbre)

def download_models():
    # Download hubert base model if not present
    if not os.path.isfile('./hubert_base.pt'):
        response = requests.get('https://huggingface.co/kindahex/voice-conversion/blob/main/hubert_base.pt')

        if response.status_code == 200:
            with open('./hubert_base.pt', 'wb') as f:
                f.write(response.content)
            print("Downloaded hubert base model file successfully. File saved to ./hubert_base.pt.")
        else:
            raise Exception("Failed to download hubert base model file. Status code: " + str(response.status_code) + ".")
        
    # Download rmvpe model if not present
    if not os.path.isfile('./rmvpe.pt'):
        response = requests.get('https://huggingface.co/kindahex/voice-conversion/blob/main/rmvpe.pt')

        if response.status_code == 200:
            with open('./rmvpe.pt', 'wb') as f:
                f.write(response.content)
            print("Downloaded rmvpe model file successfully. File saved to ./rmvpe.pt.")
        else:
            raise Exception("Failed to download rmvpe model file. Status code: " + str(response.status_code) + ".")

download_models()

print("\n-------------------------------\nRVC v2 - GORGE RVC\n-------------------------------\n")

def formant_apply(qfrency, tmbre):
    Quefrency = qfrency
    Timbre = tmbre
    DoFormant = True
    CSVutil('csvdb/formanting.csv', 'w+', 'formanting', DoFormant, qfrency, tmbre)
    
    return ({"value": Quefrency, "__type__": "update"}, {"value": Timbre, "__type__": "update"})

def get_fshift_presets():
    fshift_presets_list = []
    for dirpath, _, filenames in os.walk("./formantshiftcfg/"):
        for filename in filenames:
            if filename.endswith(".txt"):
                fshift_presets_list.append(os.path.join(dirpath,filename).replace('\\','/'))
                
    if len(fshift_presets_list) > 0:
        return fshift_presets_list
    else:
        return ''



def formant_enabled(cbox, qfrency, tmbre, frmntapply, formantpreset, formant_refresh_button):
    
    if (cbox):

        DoFormant = True
        CSVutil('csvdb/formanting.csv', 'w+', 'formanting', DoFormant, qfrency, tmbre)
        #print(f"is checked? - {cbox}\ngot {DoFormant}")
        
        return (
            {"value": True, "__type__": "update"},
            {"visible": True, "__type__": "update"},
            {"visible": True, "__type__": "update"},
            {"visible": True, "__type__": "update"},
            {"visible": True, "__type__": "update"},
            {"visible": True, "__type__": "update"},
        )
        
        
    else:
        
        DoFormant = False
        CSVutil('csvdb/formanting.csv', 'w+', 'formanting', DoFormant, qfrency, tmbre)
        
        #print(f"is checked? - {cbox}\ngot {DoFormant}")
        return (
            {"value": False, "__type__": "update"},
            {"visible": False, "__type__": "update"},
            {"visible": False, "__type__": "update"},
            {"visible": False, "__type__": "update"},
            {"visible": False, "__type__": "update"},
            {"visible": False, "__type__": "update"},
            {"visible": False, "__type__": "update"},
        )
        


def preset_apply(preset, qfer, tmbr):
    if str(preset) != '':
        with open(str(preset), 'r') as p:
            content = p.readlines()
            qfer, tmbr = content[0].split('\n')[0], content[1]
            
            formant_apply(qfer, tmbr)
    else:
        pass
    return ({"value": qfer, "__type__": "update"}, {"value": tmbr, "__type__": "update"})

def update_fshift_presets(preset, qfrency, tmbre):
    
    qfrency, tmbre = preset_apply(preset, qfrency, tmbre)
    
    if (str(preset) != ''):
        with open(str(preset), 'r') as p:
            content = p.readlines()
            qfrency, tmbre = content[0].split('\n')[0], content[1]
            
            formant_apply(qfrency, tmbre)
    else:
        pass
    return (
        {"choices": get_fshift_presets(), "__type__": "update"},
        {"value": qfrency, "__type__": "update"},
        {"value": tmbre, "__type__": "update"},
    )

i18n = I18nAuto()
#i18n.print()
# 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 (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 (
            "10" in gpu_name
            or "16" 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 "A60" in gpu_name.upper()
            or "70" in gpu_name
            or "80" in gpu_name
            or "90" in gpu_name
            or "M4" in gpu_name.upper()
            or "T4" in gpu_name.upper()
            or "TITAN" in gpu_name.upper()
        ):  # 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 == True 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])
from lib.infer_pack.models import (
    SynthesizerTrnMs256NSFsid,
    SynthesizerTrnMs256NSFsid_nono,
    SynthesizerTrnMs768NSFsid,
    SynthesizerTrnMs768NSFsid_nono,
)
import soundfile as sf
from fairseq import checkpoint_utils
import gradio as gr
import logging
from vc_infer_pipeline import VC
from config import Config

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

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(config.device)
    if config.is_half:
        hubert_model = hubert_model.half()
    else:
        hubert_model = hubert_model.float()
    hubert_model.eval()


weight_root = "weights"
index_root = "logs"
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))



def vc_single(
    sid,
    input_audio_path,
    f0_up_key,
    f0_file,
    f0_method,
    file_index,
    #file_index2,
    # file_big_npy,
    index_rate,
    filter_radius,
    resample_sr,
    rms_mix_rate,
    protect,
    crepe_hop_length,
):  # spk_item, input_audio0, vc_transform0,f0_file,f0method0
    global tgt_sr, net_g, vc, hubert_model, version
    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, DoFormant, Quefrency, Timbre)
        audio_max = np.abs(audio).max() / 0.95
        if audio_max > 1:
            audio /= audio_max
        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,
            input_audio_path,
            times,
            f0_up_key,
            f0_method,
            file_index,
            # file_big_npy,
            index_rate,
            if_f0,
            filter_radius,
            tgt_sr,
            resample_sr,
            rms_mix_rate,
            version,
            protect,
            crepe_hop_length,
            f0_file=f0_file,
        )
        if resample_sr >= 16000 and tgt_sr != resample_sr:
            tgt_sr = resample_sr
        index_info = (
            "Using index:%s." % file_index
            if os.path.exists(file_index)
            else "Index not used."
        )
        return "Success.\n %s\nTime:\n npy:%ss, f0:%ss, infer:%ss" % (
            index_info,
            times[0],
            times[1],
            times[2],
        ), (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_index2,
    # file_big_npy,
    index_rate,
    filter_radius,
    resample_sr,
    rms_mix_rate,
    protect,
    format1,
    crepe_hop_length,
):
    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,
                filter_radius,
                resample_sr,
                rms_mix_rate,
                protect,
                crepe_hop_length
            )
            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.wav" % (opt_root, os.path.basename(path))
                        sf.write(
                            path,
                            audio_opt,
                            tgt_sr,
                        )
                        if os.path.exists(path):
                            os.system(
                                "ffmpeg -i %s -vn %s -q:a 2 -y"
                                % (path, path[:-4] + ".%s" % 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()

# 一个选项卡全局只能有一个音色
def get_vc(sid):
    global n_spk, tgt_sr, net_g, vc, cpt, version
    if sid == "" or 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)
            version = cpt.get("version", "v1")
            if version == "v1":
                if if_f0 == 1:
                    net_g = SynthesizerTrnMs256NSFsid(
                        *cpt["config"], is_half=config.is_half
                    )
                else:
                    net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
            elif version == "v2":
                if if_f0 == 1:
                    net_g = SynthesizerTrnMs768NSFsid(
                        *cpt["config"], is_half=config.is_half
                    )
                else:
                    net_g = SynthesizerTrnMs768NSFsid_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(person, 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)
    version = cpt.get("version", "v1")
    if version == "v1":
        if if_f0 == 1:
            net_g = SynthesizerTrnMs256NSFsid(*cpt["config"], is_half=config.is_half)
        else:
            net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
    elif version == "v2":
        if if_f0 == 1:
            net_g = SynthesizerTrnMs768NSFsid(*cpt["config"], is_half=config.is_half)
        else:
            net_g = SynthesizerTrnMs768NSFsid_nono(*cpt["config"])
    del net_g.enc_q
    print(net_g.load_state_dict(cpt["weight"], strict=False))
    net_g.eval().to(config.device)
    if config.is_half:
        net_g = net_g.half()
    else:
        net_g = net_g.float()
    vc = VC(tgt_sr, config)
    n_spk = cpt["config"][-3]
    return {"visible": False, "maximum": n_spk, "__type__": "update"}


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"}


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





global log_interval


def set_log_interval(exp_dir, batch_size12):
    log_interval = 1

    folder_path = os.path.join(exp_dir, "1_16k_wavs")

    if os.path.exists(folder_path) and os.path.isdir(folder_path):
        wav_files = [f for f in os.listdir(folder_path) if f.endswith(".wav")]
        if wav_files:
            sample_size = len(wav_files)
            log_interval = math.ceil(sample_size / batch_size12)
            if log_interval > 1:
                log_interval += 1
    return log_interval


    




def whethercrepeornah(radio):
    mango = True if radio == 'mangio-crepe' or radio == 'mangio-crepe-tiny' else False
    return ({"visible": mango, "__type__": "update"})

#                    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"}, {"__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"}


from lib.infer_pack.models_onnx import SynthesizerTrnMsNSFsidM


def export_onnx(ModelPath, ExportedPath, MoeVS=True):
    cpt = torch.load(ModelPath, map_location="cpu")
    cpt["config"][-3] = cpt["weight"]["emb_g.weight"].shape[0]  # n_spk
    hidden_channels = 256 if cpt.get("version","v1")=="v1"else 768#cpt["config"][-2]  # hidden_channels，为768Vec做准备

    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）


    net_g = SynthesizerTrnMsNSFsidM(
        *cpt["config"], is_half=False,version=cpt.get("version","v1")
    )  # 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",
    ]
    # net_g.construct_spkmixmap(n_speaker) 多角色混合轨道导出
    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,
    )
    return "Finished"

#region RVC WebUI App

def get_presets():
    data = None
    with open('../inference-presets.json', 'r') as file:
        data = json.load(file)
    preset_names = []
    for preset in data['presets']:
        preset_names.append(preset['name'])
    
    return preset_names

def change_choices2():
    audio_files=[]
    for filename in os.listdir("./audios"):
        if filename.endswith(('.wav','.mp3','.ogg','.flac','.m4a','.aac','.mp4')):
            audio_files.append(os.path.join('./audios',filename).replace('\\', '/'))
    return {"choices": sorted(audio_files), "__type__": "update"}, {"__type__": "update"}
    
audio_files=[]
for filename in os.listdir("./audios"):
    if filename.endswith(('.wav','.mp3','.ogg','.flac','.m4a','.aac','.mp4')):
        audio_files.append(os.path.join('./audios',filename).replace('\\', '/'))
        
def get_index():
    if check_for_name() != '':
        chosen_model=sorted(names)[0].split(".")[0]
        logs_path="./logs/"+chosen_model
        if os.path.exists(logs_path):
            for file in os.listdir(logs_path):
                if file.endswith(".index"):
                    return os.path.join(logs_path, file)
            return ''
        else:
            return ''
        
def get_indexes():
    indexes_list=[]
    for dirpath, dirnames, filenames in os.walk("./logs/"):
        for filename in filenames:
            if filename.endswith(".index"):
                indexes_list.append(os.path.join(dirpath,filename))
    if len(indexes_list) > 0:
        return indexes_list
    else:
        return ''
        
def get_name():
    if len(audio_files) > 0:
        return sorted(audio_files)[0]
    else:
        return ''
        
def save_to_wav(record_button):
    if record_button is None:
        pass
    else:
        path_to_file=record_button
        new_name = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")+'.wav'
        new_path='./audios/'+new_name
        shutil.move(path_to_file,new_path)
        return new_path
    
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 match_index(sid0):
    folder=sid0.split(".")[0]
    parent_dir="./logs/"+folder
    if os.path.exists(parent_dir):
        for filename in os.listdir(parent_dir):
            if filename.endswith(".index"):
                index_path=os.path.join(parent_dir,filename)
                return index_path
    else:
        return ''
                
def check_for_name():
    if len(names) > 0:
        return sorted(names)[0]
    else:
        return ''
            
def download_from_url(url, model):
    if url == '':
        return "URL cannot be left empty."
    if model =='':
        return "You need to name your model. For example: My-Model"
    url = url.strip()
    zip_dirs = ["zips", "unzips"]
    for directory in zip_dirs:
        if os.path.exists(directory):
            shutil.rmtree(directory)
    os.makedirs("zips", exist_ok=True)
    os.makedirs("unzips", exist_ok=True)
    zipfile = model + '.zip'
    zipfile_path = './zips/' + zipfile
    try:
        if "drive.google.com" in url:
            subprocess.run(["gdown", url, "--fuzzy", "-O", zipfile_path])
        elif "mega.nz" in url:
            m = Mega()
            m.download_url(url, './zips')
        else:
            subprocess.run(["wget", url, "-O", zipfile_path])
        for filename in os.listdir("./zips"):
            if filename.endswith(".zip"):
                zipfile_path = os.path.join("./zips/",filename)
                shutil.unpack_archive(zipfile_path, "./unzips", 'zip')
            else:
                return "No zipfile found."
        for root, dirs, files in os.walk('./unzips'):
            for file in files:
                file_path = os.path.join(root, file)
                if file.endswith(".index"):
                    os.mkdir(f'./logs/{model}')
                    shutil.copy2(file_path,f'./logs/{model}')
                elif "G_" not in file and "D_" not in file and file.endswith(".pth"):
                    shutil.copy(file_path,f'./weights/{model}.pth')
        shutil.rmtree("zips")
        shutil.rmtree("unzips")
        return "Success."
    except:
        return "There's been an error."
def success_message(face):
    return f'{face.name} has been uploaded.', 'None'
def mouth(size, face, voice, faces):
    if size == 'Half':
        size = 2
    else:
        size = 1
    if faces == 'None':
        character = face.name
    else:
        if faces == 'Ben Shapiro':
            character = '/content/wav2lip-HD/inputs/ben-shapiro-10.mp4'
        elif faces == 'Andrew Tate':
            character = '/content/wav2lip-HD/inputs/tate-7.mp4'
    command = "python inference.py " \
            "--checkpoint_path checkpoints/wav2lip.pth " \
            f"--face {character} " \
            f"--audio {voice} " \
            "--pads 0 20 0 0 " \
            "--outfile /content/wav2lip-HD/outputs/result.mp4 " \
            "--fps 24 " \
            f"--resize_factor {size}"
    process = subprocess.Popen(command, shell=True, cwd='/content/wav2lip-HD/Wav2Lip-master')
    stdout, stderr = process.communicate()
    return '/content/wav2lip-HD/outputs/result.mp4', 'Animation completed.'
eleven_voices = ['Adam','Antoni','Josh','Arnold','Sam','Bella','Rachel','Domi','Elli']
eleven_voices_ids=['pNInz6obpgDQGcFmaJgB','ErXwobaYiN019PkySvjV','TxGEqnHWrfWFTfGW9XjX','VR6AewLTigWG4xSOukaG','yoZ06aMxZJJ28mfd3POQ','EXAVITQu4vr4xnSDxMaL','21m00Tcm4TlvDq8ikWAM','AZnzlk1XvdvUeBnXmlld','MF3mGyEYCl7XYWbV9V6O']
chosen_voice = dict(zip(eleven_voices, eleven_voices_ids))

def stoptraining(mim): 
    if int(mim) == 1:
        try:
            CSVutil('csvdb/stop.csv', 'w+', 'stop', 'True')
            os.kill(PID, signal.SIGTERM)
        except Exception as e:
            print(f"Couldn't click due to {e}")
    return (
        {"visible": False, "__type__": "update"}, 
        {"visible": True, "__type__": "update"},
    )


def elevenTTS(xiapi, text, id, lang):
    if xiapi!= '' and id !='': 
        choice = chosen_voice[id]
        CHUNK_SIZE = 1024
        url = f"https://api.elevenlabs.io/v1/text-to-speech/{choice}"
        headers = {
        "Accept": "audio/mpeg",
        "Content-Type": "application/json",
        "xi-api-key": xiapi
        }
        if lang == 'en':
            data = {
            "text": text,
            "model_id": "eleven_monolingual_v1",
            "voice_settings": {
            "stability": 0.5,
            "similarity_boost": 0.5
            }
            }
        else:
            data = {
            "text": text,
            "model_id": "eleven_multilingual_v1",
            "voice_settings": {
            "stability": 0.5,
            "similarity_boost": 0.5
            }
            }

        response = requests.post(url, json=data, headers=headers)
        with open('./temp_eleven.mp3', 'wb') as f:
          for chunk in response.iter_content(chunk_size=CHUNK_SIZE):
              if chunk:
                  f.write(chunk)
        aud_path = save_to_wav('./temp_eleven.mp3')
        return aud_path, aud_path
    else:
        tts = gTTS(text, lang=lang)
        tts.save('./temp_gTTS.mp3')
        aud_path = save_to_wav('./temp_gTTS.mp3')
        return aud_path, aud_path


    
def zip_downloader(model):
    if not os.path.exists(f'./weights/{model}.pth'):
        return {"__type__": "update"}, f'Make sure the Voice Name is correct. I could not find {model}.pth'
    index_found = False
    for file in os.listdir(f'./logs/{model}'):
        if file.endswith('.index') and 'added' in file:
            log_file = file
            index_found = True
    if index_found:
        return [f'./weights/{model}.pth', f'./logs/{model}/{log_file}'], "Done"
    else:
        return f'./weights/{model}.pth', "Could not find Index file."