import os import sys from dotenv import load_dotenv now_dir = os.getcwd() sys.path.append(now_dir) load_dotenv() from infer.modules.vc.modules import VC from infer.modules.uvr5.modules import uvr from infer.lib.train.process_ckpt import ( change_info, extract_small_model, merge, show_info, ) from i18n.i18n import I18nAuto from configs.config import Config from sklearn.cluster import MiniBatchKMeans import torch, platform import numpy as np import gradio as gr import faiss import fairseq import pathlib import json from time import sleep from subprocess import Popen from random import shuffle import warnings import traceback import threading import shutil import logging logging.getLogger("numba").setLevel(logging.WARNING) logging.getLogger("httpx").setLevel(logging.WARNING) logger = logging.getLogger(__name__) tmp = os.path.join(now_dir, "TEMP") shutil.rmtree(tmp, ignore_errors=True) shutil.rmtree("%s/runtime/Lib/site-packages/infer_pack" % (now_dir), ignore_errors=True) shutil.rmtree("%s/runtime/Lib/site-packages/uvr5_pack" % (now_dir), ignore_errors=True) os.makedirs(tmp, exist_ok=True) os.makedirs(os.path.join(now_dir, "logs"), exist_ok=True) os.makedirs(os.path.join(now_dir, "assets/weights"), exist_ok=True) os.environ["TEMP"] = tmp warnings.filterwarnings("ignore") torch.manual_seed(114514) config = Config() vc = VC(config) if config.dml == True: def forward_dml(ctx, x, scale): ctx.scale = scale res = x.clone().detach() return res fairseq.modules.grad_multiply.GradMultiply.forward = forward_dml i18n = I18nAuto() logger.info(i18n) # 判断是否有能用来训练和加速推理的N卡 ngpu = torch.cuda.device_count() gpu_infos = [] mem = [] if_gpu_ok = False if torch.cuda.is_available() or ngpu != 0: for i in range(ngpu): gpu_name = torch.cuda.get_device_name(i) if any( value in gpu_name.upper() for value in [ "10", "16", "20", "30", "40", "A2", "A3", "A4", "P4", "A50", "500", "A60", "70", "80", "90", "M4", "T4", "TITAN", "4060", "L", "6000", ] ): # A10#A100#V100#A40#P40#M40#K80#A4500 if_gpu_ok = True # 至少有一张能用的N卡 gpu_infos.append("%s\t%s" % (i, gpu_name)) mem.append( int( torch.cuda.get_device_properties(i).total_memory / 1024 / 1024 / 1024 + 0.4 ) ) if if_gpu_ok and len(gpu_infos) > 0: gpu_info = "\n".join(gpu_infos) default_batch_size = min(mem) // 2 else: gpu_info = i18n("很遗憾您这没有能用的显卡来支持您训练") default_batch_size = 1 gpus = "-".join([i[0] for i in gpu_infos]) class ToolButton(gr.Button, gr.components.FormComponent): """Small button with single emoji as text, fits inside gradio forms""" def __init__(self, **kwargs): super().__init__(variant="tool", **kwargs) def get_block_name(self): return "button" weight_root = os.getenv("weight_root") weight_uvr5_root = os.getenv("weight_uvr5_root") index_root = os.getenv("index_root") outside_index_root = os.getenv("outside_index_root") names = [] for name in os.listdir(weight_root): if name.endswith(".pth"): names.append(name) index_paths = [] def lookup_indices(index_root): global index_paths for root, dirs, files in os.walk(index_root, topdown=False): for name in files: if name.endswith(".index") and "trained" not in name: index_paths.append("%s/%s" % (root, name)) lookup_indices(index_root) lookup_indices(outside_index_root) uvr5_names = [] for name in os.listdir(weight_uvr5_root): if name.endswith(".pth") or "onnx" in name: uvr5_names.append(name.replace(".pth", "")) def change_choices(): names = [] for name in os.listdir(weight_root): if name.endswith(".pth"): names.append(name) index_paths = [] for root, dirs, files in os.walk(index_root, topdown=False): for name in files: if name.endswith(".index") and "trained" not in name: index_paths.append("%s/%s" % (root, name)) return {"choices": sorted(names), "__type__": "update"}, { "choices": sorted(index_paths), "__type__": "update", } def clean(): return {"value": "", "__type__": "update"} def export_onnx(ModelPath, ExportedPath): from infer.modules.onnx.export import export_onnx as eo eo(ModelPath, ExportedPath) sr_dict = { "32k": 32000, "40k": 40000, "48k": 48000, } def if_done(done, p): while 1: if p.poll() is None: sleep(0.5) else: break done[0] = True def if_done_multi(done, ps): while 1: # poll==None代表进程未结束 # 只要有一个进程未结束都不停 flag = 1 for p in ps: if p.poll() is None: flag = 0 sleep(0.5) break if flag == 1: break done[0] = True def preprocess_dataset(trainset_dir, exp_dir, sr, n_p): sr = sr_dict[sr] os.makedirs("%s/logs/%s" % (now_dir, exp_dir), exist_ok=True) f = open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "w") f.close() cmd = '"%s" infer/modules/train/preprocess.py "%s" %s %s "%s/logs/%s" %s %.1f' % ( config.python_cmd, trainset_dir, sr, n_p, now_dir, exp_dir, config.noparallel, config.preprocess_per, ) logger.info("Execute: " + cmd) # , stdin=PIPE, stdout=PIPE,stderr=PIPE,cwd=now_dir p = Popen(cmd, shell=True) # 煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读 done = [False] threading.Thread( target=if_done, args=( done, p, ), ).start() while 1: with open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "r") as f: yield (f.read()) sleep(1) if done[0]: break with open("%s/logs/%s/preprocess.log" % (now_dir, exp_dir), "r") as f: log = f.read() logger.info(log) yield log # but2.click(extract_f0,[gpus6,np7,f0method8,if_f0_3,trainset_dir4],[info2]) def extract_f0_feature(gpus, n_p, f0method, if_f0, exp_dir, version19, gpus_rmvpe): gpus = gpus.split("-") os.makedirs("%s/logs/%s" % (now_dir, exp_dir), exist_ok=True) f = open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "w") f.close() if if_f0: if f0method != "rmvpe_gpu": cmd = ( '"%s" infer/modules/train/extract/extract_f0_print.py "%s/logs/%s" %s %s' % ( config.python_cmd, now_dir, exp_dir, n_p, f0method, ) ) logger.info("Execute: " + cmd) p = Popen( cmd, shell=True, cwd=now_dir ) # , stdin=PIPE, stdout=PIPE,stderr=PIPE # 煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读 done = [False] threading.Thread( target=if_done, args=( done, p, ), ).start() else: if gpus_rmvpe != "-": gpus_rmvpe = gpus_rmvpe.split("-") leng = len(gpus_rmvpe) ps = [] for idx, n_g in enumerate(gpus_rmvpe): cmd = ( '"%s" infer/modules/train/extract/extract_f0_rmvpe.py %s %s %s "%s/logs/%s" %s ' % ( config.python_cmd, leng, idx, n_g, now_dir, exp_dir, config.is_half, ) ) logger.info("Execute: " + cmd) p = Popen( cmd, shell=True, cwd=now_dir ) # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir ps.append(p) # 煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读 done = [False] threading.Thread( target=if_done_multi, # args=( done, ps, ), ).start() else: cmd = ( config.python_cmd + ' infer/modules/train/extract/extract_f0_rmvpe_dml.py "%s/logs/%s" ' % ( now_dir, exp_dir, ) ) logger.info("Execute: " + cmd) p = Popen( cmd, shell=True, cwd=now_dir ) # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir p.wait() done = [True] while 1: with open( "%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r" ) as f: yield (f.read()) sleep(1) if done[0]: break with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f: log = f.read() logger.info(log) yield log # 对不同part分别开多进程 """ n_part=int(sys.argv[1]) i_part=int(sys.argv[2]) i_gpu=sys.argv[3] exp_dir=sys.argv[4] os.environ["CUDA_VISIBLE_DEVICES"]=str(i_gpu) """ leng = len(gpus) ps = [] for idx, n_g in enumerate(gpus): cmd = ( '"%s" infer/modules/train/extract_feature_print.py %s %s %s %s "%s/logs/%s" %s %s' % ( config.python_cmd, config.device, leng, idx, n_g, now_dir, exp_dir, version19, config.is_half, ) ) logger.info("Execute: " + cmd) p = Popen( cmd, shell=True, cwd=now_dir ) # , shell=True, stdin=PIPE, stdout=PIPE, stderr=PIPE, cwd=now_dir ps.append(p) # 煞笔gr, popen read都非得全跑完了再一次性读取, 不用gr就正常读一句输出一句;只能额外弄出一个文本流定时读 done = [False] threading.Thread( target=if_done_multi, args=( done, ps, ), ).start() while 1: with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f: yield (f.read()) sleep(1) if done[0]: break with open("%s/logs/%s/extract_f0_feature.log" % (now_dir, exp_dir), "r") as f: log = f.read() logger.info(log) yield log def get_pretrained_models(path_str, f0_str, sr2): if_pretrained_generator_exist = os.access( "assets/pretrained%s/%sG%s.pth" % (path_str, f0_str, sr2), os.F_OK ) if_pretrained_discriminator_exist = os.access( "assets/pretrained%s/%sD%s.pth" % (path_str, f0_str, sr2), os.F_OK ) if not if_pretrained_generator_exist: logger.warning( "assets/pretrained%s/%sG%s.pth not exist, will not use pretrained model", path_str, f0_str, sr2, ) if not if_pretrained_discriminator_exist: logger.warning( "assets/pretrained%s/%sD%s.pth not exist, will not use pretrained model", path_str, f0_str, sr2, ) return ( ( "assets/pretrained%s/%sG%s.pth" % (path_str, f0_str, sr2) if if_pretrained_generator_exist else "" ), ( "assets/pretrained%s/%sD%s.pth" % (path_str, f0_str, sr2) if if_pretrained_discriminator_exist else "" ), ) def change_sr2(sr2, if_f0_3, version19): path_str = "" if version19 == "v1" else "_v2" f0_str = "f0" if if_f0_3 else "" return get_pretrained_models(path_str, f0_str, sr2) def change_version19(sr2, if_f0_3, version19): path_str = "" if version19 == "v1" else "_v2" if sr2 == "32k" and version19 == "v1": sr2 = "40k" to_return_sr2 = ( {"choices": ["40k", "48k"], "__type__": "update", "value": sr2} if version19 == "v1" else {"choices": ["40k", "48k", "32k"], "__type__": "update", "value": sr2} ) f0_str = "f0" if if_f0_3 else "" return ( *get_pretrained_models(path_str, f0_str, sr2), to_return_sr2, ) def change_f0(if_f0_3, sr2, version19): # f0method8,pretrained_G14,pretrained_D15 path_str = "" if version19 == "v1" else "_v2" return ( {"visible": if_f0_3, "__type__": "update"}, {"visible": if_f0_3, "__type__": "update"}, *get_pretrained_models(path_str, "f0" if if_f0_3 == True else "", sr2), ) # but3.click(click_train,[exp_dir1,sr2,if_f0_3,save_epoch10,total_epoch11,batch_size12,if_save_latest13,pretrained_G14,pretrained_D15,gpus16]) def click_train( exp_dir1, sr2, if_f0_3, spk_id5, save_epoch10, total_epoch11, batch_size12, if_save_latest13, pretrained_G14, pretrained_D15, gpus16, if_cache_gpu17, if_save_every_weights18, version19, ): # 生成filelist exp_dir = "%s/logs/%s" % (now_dir, exp_dir1) os.makedirs(exp_dir, exist_ok=True) gt_wavs_dir = "%s/0_gt_wavs" % (exp_dir) feature_dir = ( "%s/3_feature256" % (exp_dir) if version19 == "v1" else "%s/3_feature768" % (exp_dir) ) if if_f0_3: f0_dir = "%s/2a_f0" % (exp_dir) f0nsf_dir = "%s/2b-f0nsf" % (exp_dir) names = ( set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)]) & set([name.split(".")[0] for name in os.listdir(feature_dir)]) & set([name.split(".")[0] for name in os.listdir(f0_dir)]) & set([name.split(".")[0] for name in os.listdir(f0nsf_dir)]) ) else: names = set([name.split(".")[0] for name in os.listdir(gt_wavs_dir)]) & set( [name.split(".")[0] for name in os.listdir(feature_dir)] ) opt = [] for name in names: if if_f0_3: opt.append( "%s/%s.wav|%s/%s.npy|%s/%s.wav.npy|%s/%s.wav.npy|%s" % ( gt_wavs_dir.replace("\\", "\\\\"), name, feature_dir.replace("\\", "\\\\"), name, f0_dir.replace("\\", "\\\\"), name, f0nsf_dir.replace("\\", "\\\\"), name, spk_id5, ) ) else: opt.append( "%s/%s.wav|%s/%s.npy|%s" % ( gt_wavs_dir.replace("\\", "\\\\"), name, feature_dir.replace("\\", "\\\\"), name, spk_id5, ) ) fea_dim = 256 if version19 == "v1" else 768 if if_f0_3: for _ in range(2): opt.append( "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s/logs/mute/2a_f0/mute.wav.npy|%s/logs/mute/2b-f0nsf/mute.wav.npy|%s" % (now_dir, sr2, now_dir, fea_dim, now_dir, now_dir, spk_id5) ) else: for _ in range(2): opt.append( "%s/logs/mute/0_gt_wavs/mute%s.wav|%s/logs/mute/3_feature%s/mute.npy|%s" % (now_dir, sr2, now_dir, fea_dim, spk_id5) ) shuffle(opt) with open("%s/filelist.txt" % exp_dir, "w") as f: f.write("\n".join(opt)) logger.debug("Write filelist done") # 生成config#无需生成config # cmd = python_cmd + " train_nsf_sim_cache_sid_load_pretrain.py -e mi-test -sr 40k -f0 1 -bs 4 -g 0 -te 10 -se 5 -pg pretrained/f0G40k.pth -pd pretrained/f0D40k.pth -l 1 -c 0" logger.info("Use gpus: %s", str(gpus16)) if pretrained_G14 == "": logger.info("No pretrained Generator") if pretrained_D15 == "": logger.info("No pretrained Discriminator") if version19 == "v1" or sr2 == "40k": config_path = "v1/%s.json" % sr2 else: config_path = "v2/%s.json" % sr2 config_save_path = os.path.join(exp_dir, "config.json") if not pathlib.Path(config_save_path).exists(): with open(config_save_path, "w", encoding="utf-8") as f: json.dump( config.json_config[config_path], f, ensure_ascii=False, indent=4, sort_keys=True, ) f.write("\n") if gpus16: cmd = ( '"%s" infer/modules/train/train.py -e "%s" -sr %s -f0 %s -bs %s -g %s -te %s -se %s %s %s -l %s -c %s -sw %s -v %s' % ( config.python_cmd, exp_dir1, sr2, 1 if if_f0_3 else 0, batch_size12, gpus16, total_epoch11, save_epoch10, "-pg %s" % pretrained_G14 if pretrained_G14 != "" else "", "-pd %s" % pretrained_D15 if pretrained_D15 != "" else "", 1 if if_save_latest13 == i18n("是") else 0, 1 if if_cache_gpu17 == i18n("是") else 0, 1 if if_save_every_weights18 == i18n("是") else 0, version19, ) ) else: cmd = ( '"%s" infer/modules/train/train.py -e "%s" -sr %s -f0 %s -bs %s -te %s -se %s %s %s -l %s -c %s -sw %s -v %s' % ( config.python_cmd, exp_dir1, sr2, 1 if if_f0_3 else 0, batch_size12, total_epoch11, save_epoch10, "-pg %s" % pretrained_G14 if pretrained_G14 != "" else "", "-pd %s" % pretrained_D15 if pretrained_D15 != "" else "", 1 if if_save_latest13 == i18n("是") else 0, 1 if if_cache_gpu17 == i18n("是") else 0, 1 if if_save_every_weights18 == i18n("是") else 0, version19, ) ) logger.info("Execute: " + cmd) p = Popen(cmd, shell=True, cwd=now_dir) p.wait() return "训练结束, 您可查看控制台训练日志或实验文件夹下的train.log" # but4.click(train_index, [exp_dir1], info3) def train_index(exp_dir1, version19): # exp_dir = "%s/logs/%s" % (now_dir, exp_dir1) exp_dir = "logs/%s" % (exp_dir1) os.makedirs(exp_dir, exist_ok=True) feature_dir = ( "%s/3_feature256" % (exp_dir) if version19 == "v1" else "%s/3_feature768" % (exp_dir) ) if not os.path.exists(feature_dir): return "请先进行特征提取!" listdir_res = list(os.listdir(feature_dir)) if len(listdir_res) == 0: return "请先进行特征提取！" infos = [] npys = [] for name in sorted(listdir_res): phone = np.load("%s/%s" % (feature_dir, name)) npys.append(phone) big_npy = np.concatenate(npys, 0) big_npy_idx = np.arange(big_npy.shape[0]) np.random.shuffle(big_npy_idx) big_npy = big_npy[big_npy_idx] if big_npy.shape[0] > 2e5: infos.append("Trying doing kmeans %s shape to 10k centers." % big_npy.shape[0]) yield "\n".join(infos) try: big_npy = ( MiniBatchKMeans( n_clusters=10000, verbose=True, batch_size=256 * config.n_cpu, compute_labels=False, init="random", ) .fit(big_npy) .cluster_centers_ ) except: info = traceback.format_exc() logger.info(info) infos.append(info) yield "\n".join(infos) np.save("%s/total_fea.npy" % exp_dir, big_npy) n_ivf = min(int(16 * np.sqrt(big_npy.shape[0])), big_npy.shape[0] // 39) infos.append("%s,%s" % (big_npy.shape, n_ivf)) yield "\n".join(infos) index = faiss.index_factory(256 if version19 == "v1" else 768, "IVF%s,Flat" % n_ivf) # index = faiss.index_factory(256if version19=="v1"else 768, "IVF%s,PQ128x4fs,RFlat"%n_ivf) infos.append("training") yield "\n".join(infos) index_ivf = faiss.extract_index_ivf(index) # index_ivf.nprobe = 1 index.train(big_npy) faiss.write_index( index, "%s/trained_IVF%s_Flat_nprobe_%s_%s_%s.index" % (exp_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19), ) infos.append("adding") yield "\n".join(infos) batch_size_add = 8192 for i in range(0, big_npy.shape[0], batch_size_add): index.add(big_npy[i : i + batch_size_add]) faiss.write_index( index, "%s/added_IVF%s_Flat_nprobe_%s_%s_%s.index" % (exp_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19), ) infos.append( "成功构建索引 added_IVF%s_Flat_nprobe_%s_%s_%s.index" % (n_ivf, index_ivf.nprobe, exp_dir1, version19) ) try: link = os.link if platform.system() == "Windows" else os.symlink link( "%s/added_IVF%s_Flat_nprobe_%s_%s_%s.index" % (exp_dir, n_ivf, index_ivf.nprobe, exp_dir1, version19), "%s/%s_IVF%s_Flat_nprobe_%s_%s_%s.index" % ( outside_index_root, exp_dir1, n_ivf, index_ivf.nprobe, exp_dir1, version19, ), ) infos.append("链接索引到外部-%s" % (outside_index_root)) except: infos.append("链接索引到外部-%s失败" % (outside_index_root)) # faiss.write_index(index, '%s/added_IVF%s_Flat_FastScan_%s.index'%(exp_dir,n_ivf,version19)) # infos.append("成功构建索引，added_IVF%s_Flat_FastScan_%s.index"%(n_ivf,version19)) yield "\n".join(infos) # but5.click(train1key, [exp_dir1, sr2, if_f0_3, trainset_dir4, spk_id5, gpus6, np7, f0method8, save_epoch10, total_epoch11, batch_size12, if_save_latest13, pretrained_G14, pretrained_D15, gpus16, if_cache_gpu17], info3) def train1key( exp_dir1, sr2, if_f0_3, trainset_dir4, spk_id5, np7, f0method8, save_epoch10, total_epoch11, batch_size12, if_save_latest13, pretrained_G14, pretrained_D15, gpus16, if_cache_gpu17, if_save_every_weights18, version19, gpus_rmvpe, ): infos = [] def get_info_str(strr): infos.append(strr) return "\n".join(infos) # step1:处理数据 yield get_info_str(i18n("step1:正在处理数据")) [get_info_str(_) for _ in preprocess_dataset(trainset_dir4, exp_dir1, sr2, np7)] # step2a:提取音高 yield get_info_str(i18n("step2:正在提取音高&正在提取特征")) [ get_info_str(_) for _ in extract_f0_feature( gpus16, np7, f0method8, if_f0_3, exp_dir1, version19, gpus_rmvpe ) ] # step3a:训练模型 yield get_info_str(i18n("step3a:正在训练模型")) click_train( exp_dir1, sr2, if_f0_3, spk_id5, save_epoch10, total_epoch11, batch_size12, if_save_latest13, pretrained_G14, pretrained_D15, gpus16, if_cache_gpu17, if_save_every_weights18, version19, ) yield get_info_str( i18n("训练结束, 您可查看控制台训练日志或实验文件夹下的train.log") ) # step3b:训练索引 [get_info_str(_) for _ in train_index(exp_dir1, version19)] yield get_info_str(i18n("全流程结束！")) # ckpt_path2.change(change_info_,[ckpt_path2],[sr__,if_f0__]) def change_info_(ckpt_path): if not os.path.exists(ckpt_path.replace(os.path.basename(ckpt_path), "train.log")): return {"__type__": "update"}, {"__type__": "update"}, {"__type__": "update"} try: with open( ckpt_path.replace(os.path.basename(ckpt_path), "train.log"), "r" ) as f: info = eval(f.read().strip("\n").split("\n")[0].split("\t")[-1]) sr, f0 = info["sample_rate"], info["if_f0"] version = "v2" if ("version" in info and info["version"] == "v2") else "v1" return sr, str(f0), version except: traceback.print_exc() return {"__type__": "update"}, {"__type__": "update"}, {"__type__": "update"} F0GPUVisible = config.dml == False def change_f0_method(f0method8): if f0method8 == "rmvpe_gpu": visible = F0GPUVisible else: visible = False return {"visible": visible, "__type__": "update"} with gr.Blocks(title="RVC WebUI") as app: gr.Markdown("## RVC WebUI") gr.Markdown( value=i18n( "本软件以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责.
如不认可该条款, 则不能使用或引用软件包内任何代码和文件. 详见根目录LICENSE." ) ) with gr.Tabs(): with gr.TabItem(i18n("训练")): gr.Markdown( value=i18n( "step1: 填写实验配置. 实验数据放在logs下, 每个实验一个文件夹, 需手工输入实验名路径, 内含实验配置, 日志, 训练得到的模型文件. " ) ) with gr.Row(): exp_dir1 = gr.Textbox(label=i18n("输入实验名"), value="mi-test") sr2 = gr.Radio( label=i18n("目标采样率"), choices=["40k", "48k"], value="40k", interactive=True, ) if_f0_3 = gr.Radio( label=i18n("模型是否带音高指导(唱歌一定要, 语音可以不要)"), choices=[True, False], value=True, interactive=True, ) version19 = gr.Radio( label=i18n("版本"), choices=["v1", "v2"], value="v2", interactive=True, visible=True, ) np7 = gr.Slider( minimum=0, maximum=config.n_cpu, step=1, label=i18n("提取音高和处理数据使用的CPU进程数"), value=int(np.ceil(config.n_cpu / 1.5)), interactive=True, ) with gr.Group(): # 暂时单人的, 后面支持最多4人的#数据处理 gr.Markdown( value=i18n( "step2a: 自动遍历训练文件夹下所有可解码成音频的文件并进行切片归一化, 在实验目录下生成2个wav文件夹; 暂时只支持单人训练. " ) ) with gr.Row(): trainset_dir4 = gr.Textbox( label=i18n("输入训练文件夹路径"), value=i18n("E:\\语音音频+标注\\米津玄师\\src"), ) spk_id5 = gr.Slider( minimum=0, maximum=4, step=1, label=i18n("请指定说话人id"), value=0, interactive=True, ) but1 = gr.Button(i18n("处理数据"), variant="primary") info1 = gr.Textbox(label=i18n("输出信息"), value="") but1.click( preprocess_dataset, [trainset_dir4, exp_dir1, sr2, np7], [info1], api_name="train_preprocess", ) with gr.Group(): gr.Markdown( value=i18n( "step2b: 使用CPU提取音高(如果模型带音高), 使用GPU提取特征(选择卡号)" ) ) with gr.Row(): with gr.Column(): gpus6 = gr.Textbox( label=i18n( "以-分隔输入使用的卡号, 例如 0-1-2 使用卡0和卡1和卡2" ), value=gpus, interactive=True, visible=F0GPUVisible, ) gpu_info9 = gr.Textbox( label=i18n("显卡信息"), value=gpu_info, visible=F0GPUVisible ) with gr.Column(): f0method8 = gr.Radio( label=i18n( "选择音高提取算法:输入歌声可用pm提速,高质量语音但CPU差可用dio提速,harvest质量更好但慢,rmvpe效果最好且微吃CPU/GPU" ), choices=["pm", "harvest", "dio", "rmvpe", "rmvpe_gpu"], value="rmvpe_gpu", interactive=True, ) gpus_rmvpe = gr.Textbox( label=i18n( "rmvpe卡号配置：以-分隔输入使用的不同进程卡号,例如0-0-1使用在卡0上跑2个进程并在卡1上跑1个进程" ), value="%s-%s" % (gpus, gpus), interactive=True, visible=F0GPUVisible, ) but2 = gr.Button(i18n("特征提取"), variant="primary") info2 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8) f0method8.change( fn=change_f0_method, inputs=[f0method8], outputs=[gpus_rmvpe], ) but2.click( extract_f0_feature, [ gpus6, np7, f0method8, if_f0_3, exp_dir1, version19, gpus_rmvpe, ], [info2], api_name="train_extract_f0_feature", ) with gr.Group(): gr.Markdown(value=i18n("step3: 填写训练设置, 开始训练模型和索引")) with gr.Row(): save_epoch10 = gr.Slider( minimum=1, maximum=50, step=1, label=i18n("保存频率save_every_epoch"), value=5, interactive=True, ) total_epoch11 = gr.Slider( minimum=2, maximum=1000, step=1, label=i18n("总训练轮数total_epoch"), value=20, interactive=True, ) batch_size12 = gr.Slider( minimum=1, maximum=40, step=1, label=i18n("每张显卡的batch_size"), value=default_batch_size, interactive=True, ) if_save_latest13 = gr.Radio( label=i18n("是否仅保存最新的ckpt文件以节省硬盘空间"), choices=[i18n("是"), i18n("否")], value=i18n("否"), interactive=True, ) if_cache_gpu17 = gr.Radio( label=i18n( "是否缓存所有训练集至显存. 10min以下小数据可缓存以加速训练, 大数据缓存会炸显存也加不了多少速" ), choices=[i18n("是"), i18n("否")], value=i18n("否"), interactive=True, ) if_save_every_weights18 = gr.Radio( label=i18n( "是否在每次保存时间点将最终小模型保存至weights文件夹" ), choices=[i18n("是"), i18n("否")], value=i18n("否"), interactive=True, ) with gr.Row(): pretrained_G14 = gr.Textbox( label=i18n("加载预训练底模G路径"), value="assets/pretrained_v2/f0G40k.pth", interactive=True, ) pretrained_D15 = gr.Textbox( label=i18n("加载预训练底模D路径"), value="assets/pretrained_v2/f0D40k.pth", interactive=True, ) sr2.change( change_sr2, [sr2, if_f0_3, version19], [pretrained_G14, pretrained_D15], ) version19.change( change_version19, [sr2, if_f0_3, version19], [pretrained_G14, pretrained_D15, sr2], ) if_f0_3.change( change_f0, [if_f0_3, sr2, version19], [f0method8, gpus_rmvpe, pretrained_G14, pretrained_D15], ) gpus16 = gr.Textbox( label=i18n( "以-分隔输入使用的卡号, 例如 0-1-2 使用卡0和卡1和卡2" ), value=gpus, interactive=True, ) but3 = gr.Button(i18n("训练模型"), variant="primary") but4 = gr.Button(i18n("训练特征索引"), variant="primary") but5 = gr.Button(i18n("一键训练"), variant="primary") info3 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=10) but3.click( click_train, [ exp_dir1, sr2, if_f0_3, spk_id5, save_epoch10, total_epoch11, batch_size12, if_save_latest13, pretrained_G14, pretrained_D15, gpus16, if_cache_gpu17, if_save_every_weights18, version19, ], info3, api_name="train_start", ) but4.click(train_index, [exp_dir1, version19], info3) but5.click( train1key, [ exp_dir1, sr2, if_f0_3, trainset_dir4, spk_id5, np7, f0method8, save_epoch10, total_epoch11, batch_size12, if_save_latest13, pretrained_G14, pretrained_D15, gpus16, if_cache_gpu17, if_save_every_weights18, version19, gpus_rmvpe, ], info3, api_name="train_start_all", ) with gr.TabItem(i18n("ckpt处理")): with gr.Group(): gr.Markdown(value=i18n("模型融合, 可用于测试音色融合")) with gr.Row(): ckpt_a = gr.Textbox( label=i18n("A模型路径"), value="", interactive=True ) ckpt_b = gr.Textbox( label=i18n("B模型路径"), value="", interactive=True ) alpha_a = gr.Slider( minimum=0, maximum=1, label=i18n("A模型权重"), value=0.5, interactive=True, ) with gr.Row(): sr_ = gr.Radio( label=i18n("目标采样率"), choices=["40k", "48k"], value="40k", interactive=True, ) if_f0_ = gr.Radio( label=i18n("模型是否带音高指导"), choices=[i18n("是"), i18n("否")], value=i18n("是"), interactive=True, ) info__ = gr.Textbox( label=i18n("要置入的模型信息"), value="", max_lines=8, interactive=True, ) name_to_save0 = gr.Textbox( label=i18n("保存的模型名不带后缀"), value="", max_lines=1, interactive=True, ) version_2 = gr.Radio( label=i18n("模型版本型号"), choices=["v1", "v2"], value="v1", interactive=True, ) with gr.Row(): but6 = gr.Button(i18n("融合"), variant="primary") info4 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8) but6.click( merge, [ ckpt_a, ckpt_b, alpha_a, sr_, if_f0_, info__, name_to_save0, version_2, ], info4, api_name="ckpt_merge", ) # def merge(path1,path2,alpha1,sr,f0,info): with gr.Group(): gr.Markdown( value=i18n("修改模型信息(仅支持weights文件夹下提取的小模型文件)") ) with gr.Row(): ckpt_path0 = gr.Textbox( label=i18n("模型路径"), value="", interactive=True ) info_ = gr.Textbox( label=i18n("要改的模型信息"), value="", max_lines=8, interactive=True, ) name_to_save1 = gr.Textbox( label=i18n("保存的文件名, 默认空为和源文件同名"), value="", max_lines=8, interactive=True, ) with gr.Row(): but7 = gr.Button(i18n("修改"), variant="primary") info5 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8) but7.click( change_info, [ckpt_path0, info_, name_to_save1], info5, api_name="ckpt_modify", ) with gr.Group(): gr.Markdown( value=i18n("查看模型信息(仅支持weights文件夹下提取的小模型文件)") ) with gr.Row(): ckpt_path1 = gr.Textbox( label=i18n("模型路径"), value="", interactive=True ) but8 = gr.Button(i18n("查看"), variant="primary") info6 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8) but8.click(show_info, [ckpt_path1], info6, api_name="ckpt_show") with gr.Group(): gr.Markdown( value=i18n( "模型提取(输入logs文件夹下大文件模型路径),适用于训一半不想训了模型没有自动提取保存小文件模型,或者想测试中间模型的情况" ) ) with gr.Row(): ckpt_path2 = gr.Textbox( label=i18n("模型路径"), value="E:\\codes\\py39\\logs\\mi-test_f0_48k\\G_23333.pth", interactive=True, ) save_name = gr.Textbox( label=i18n("保存名"), value="", interactive=True ) sr__ = gr.Radio( label=i18n("目标采样率"), choices=["32k", "40k", "48k"], value="40k", interactive=True, ) if_f0__ = gr.Radio( label=i18n("模型是否带音高指导,1是0否"), choices=["1", "0"], value="1", interactive=True, ) version_1 = gr.Radio( label=i18n("模型版本型号"), choices=["v1", "v2"], value="v2", interactive=True, ) info___ = gr.Textbox( label=i18n("要置入的模型信息"), value="", max_lines=8, interactive=True, ) but9 = gr.Button(i18n("提取"), variant="primary") info7 = gr.Textbox(label=i18n("输出信息"), value="", max_lines=8) ckpt_path2.change( change_info_, [ckpt_path2], [sr__, if_f0__, version_1] ) but9.click( extract_small_model, [ckpt_path2, save_name, sr__, if_f0__, info___, version_1], info7, api_name="ckpt_extract", ) with gr.TabItem(i18n("Onnx导出")): with gr.Row(): ckpt_dir = gr.Textbox( label=i18n("RVC模型路径"), value="", interactive=True ) with gr.Row(): onnx_dir = gr.Textbox( label=i18n("Onnx输出路径"), value="", interactive=True ) with gr.Row(): infoOnnx = gr.Label(label="info") with gr.Row(): butOnnx = gr.Button(i18n("导出Onnx模型"), variant="primary") butOnnx.click( export_onnx, [ckpt_dir, onnx_dir], infoOnnx, api_name="export_onnx" ) tab_faq = i18n("常见问题解答") with gr.TabItem(tab_faq): try: if tab_faq == "常见问题解答": with open("docs/cn/faq.md", "r", encoding="utf8") as f: info = f.read() else: with open("docs/en/faq_en.md", "r", encoding="utf8") as f: info = f.read() gr.Markdown(value=info) except: gr.Markdown(traceback.format_exc()) if config.iscolab: app.queue(concurrency_count=511, max_size=1022).launch(share=True) else: app.queue(concurrency_count=511, max_size=1022).launch( server_name="0.0.0.0", inbrowser=not config.noautoopen, server_port=config.listen_port, quiet=True, )