From 99404baf945c6842df50656f06b494a14341a347 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" <41898282+github-actions[bot]@users.noreply.github.com> Date: Sat, 3 Jun 2023 08:22:46 +0000 Subject: [PATCH] Format code (#409) Co-authored-by: github-actions[bot] --- app.py | 181 +++++++++++------------ train_nsf_sim_cache_sid_load_pretrain.py | 7 +- 2 files changed, 93 insertions(+), 95 deletions(-) diff --git a/app.py b/app.py index 0a809ca..8688973 100644 --- a/app.py +++ b/app.py @@ -1,6 +1,7 @@ import io import os import torch + # os.system("wget -P cvec/ https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt") import gradio as gr import librosa @@ -20,10 +21,10 @@ from infer_pack.models import ( ) from i18n import I18nAuto -logging.getLogger('numba').setLevel(logging.WARNING) -logging.getLogger('markdown_it').setLevel(logging.WARNING) -logging.getLogger('urllib3').setLevel(logging.WARNING) -logging.getLogger('matplotlib').setLevel(logging.WARNING) +logging.getLogger("numba").setLevel(logging.WARNING) +logging.getLogger("markdown_it").setLevel(logging.WARNING) +logging.getLogger("urllib3").setLevel(logging.WARNING) +logging.getLogger("matplotlib").setLevel(logging.WARNING) i18n = I18nAuto() i18n.print() @@ -44,7 +45,7 @@ for root, dirs, files in os.walk(index_root, topdown=False): if name.endswith(".index") and "trained" not in name: index_paths.append("%s/%s" % (root, name)) - + def get_vc(sid): global n_spk, tgt_sr, net_g, vc, cpt, version if sid == "" or sid == []: @@ -121,7 +122,6 @@ def load_hubert(): hubert_model.eval() - def vc_single( sid, input_audio_path, @@ -144,7 +144,7 @@ def vc_single( try: audio = input_audio_path[1] / 32768.0 if len(audio.shape) == 2: - audio = np.mean(audio,-1) + audio = np.mean(audio, -1) audio = librosa.resample(audio, orig_sr=input_audio_path[0], target_sr=16000) audio_max = np.abs(audio).max() / 0.95 if audio_max > 1: @@ -212,114 +212,111 @@ app = gr.Blocks() with app: with gr.Tabs(): with gr.TabItem("在线demo"): - gr.Markdown(value=""" + gr.Markdown( + value=""" RVC 在线demo - """) + """ + ) sid = gr.Dropdown(label=i18n("推理音色"), choices=sorted(names)) with gr.Column(): 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, - ) + minimum=0, + maximum=2333, + step=1, + label=i18n("请选择说话人id"), + value=0, + visible=False, + interactive=True, + ) sid.change( - fn=get_vc, - inputs=[sid], - outputs=[spk_item], + fn=get_vc, + inputs=[sid], + outputs=[spk_item], ) gr.Markdown( value=i18n("男转女推荐+12key, 女转男推荐-12key, 如果音域爆炸导致音色失真也可以自己调整到合适音域. ") ) vc_input3 = gr.Audio(label="上传音频（长度小于90秒）") - vc_transform0 = gr.Number( - label=i18n("变调(整数, 半音数量, 升八度12降八度-12)"), value=0 - ) + vc_transform0 = gr.Number(label=i18n("变调(整数, 半音数量, 升八度12降八度-12)"), value=0) 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" - ), - choices=["pm", "harvest", "crepe"], - value="pm", - interactive=True, - ) + 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"), + choices=["pm", "harvest", "crepe"], + value="pm", + 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, - ) + 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, + ) with gr.Column(): 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"), - value="", - interactive=False, - visible=False - ) + label=i18n("特征检索库文件路径,为空则使用下拉的选择结果"), + value="", + interactive=False, + visible=False, + ) 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, - ) + label=i18n("自动检测index路径,下拉式选择(dropdown)"), + choices=sorted(index_paths), + interactive=True, + ) index_rate1 = gr.Slider( - minimum=0, - maximum=1, - label=i18n("检索特征占比"), - value=0.88, - interactive=True, - ) + minimum=0, + maximum=1, + label=i18n("检索特征占比"), + value=0.88, + interactive=True, + ) 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, - ) + 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=1, - interactive=True, - ) + minimum=0, + maximum=1, + label=i18n("输入源音量包络替换输出音量包络融合比例，越靠近1越使用输出包络"), + value=1, + interactive=True, + ) 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, - ) + 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, + ) 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")) but0 = gr.Button(i18n("转换"), variant="primary") 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_single, - [ - spk_item, - vc_input3, - 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], - ) + but0.click( + vc_single, + [ + spk_item, + vc_input3, + 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], + ) app.launch() diff --git a/train_nsf_sim_cache_sid_load_pretrain.py b/train_nsf_sim_cache_sid_load_pretrain.py index bc64e5f..112888f 100644 --- a/train_nsf_sim_cache_sid_load_pretrain.py +++ b/train_nsf_sim_cache_sid_load_pretrain.py @@ -9,7 +9,7 @@ import datetime hps = utils.get_hparams() os.environ["CUDA_VISIBLE_DEVICES"] = hps.gpus.replace("-", ",") n_gpus = len(hps.gpus.split("-")) -from random import shuffle,randint +from random import shuffle, randint import traceback, json, argparse, itertools, math, torch, pdb torch.backends.cudnn.deterministic = False @@ -67,9 +67,10 @@ class EpochRecorder: def main(): n_gpus = torch.cuda.device_count() - if torch.cuda.is_available()==False and torch.backends.mps.is_available()==True:n_gpus = 1 + if torch.cuda.is_available() == False and torch.backends.mps.is_available() == True: + n_gpus = 1 os.environ["MASTER_ADDR"] = "localhost" - os.environ["MASTER_PORT"] = str(randint(20000,55555)) + os.environ["MASTER_PORT"] = str(randint(20000, 55555)) children = [] for i in range(n_gpus): subproc = mp.Process(