mirror of
https://github.com/svc-develop-team/so-vits-svc.git
synced 2025-01-09 04:27:31 +08:00
Beautify webui and remove app.py
This commit is contained in:
SherkeyXD
parent
e0b7261aa0
commit
94b2063b43
69
app.py
69
app.py
@ -1,69 +0,0 @@
|
||||
import io
|
||||
import os
|
||||
|
||||
# os.system("wget -P cvec/ https://huggingface.co/spaces/innnky/nanami/resolve/main/checkpoint_best_legacy_500.pt")
|
||||
import gradio as gr
|
||||
import librosa
|
||||
import numpy as np
|
||||
import soundfile
|
||||
from inference.infer_tool import Svc
|
||||
import logging
|
||||
|
||||
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)
|
||||
|
||||
config_path = "configs/config.json"
|
||||
|
||||
model = Svc("logs/44k/G_114400.pth", "configs/config.json", cluster_model_path="logs/44k/kmeans_10000.pt")
|
||||
|
||||
|
||||
|
||||
def vc_fn(sid, input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, noise_scale):
|
||||
if input_audio is None:
|
||||
return "You need to upload an audio", None
|
||||
sampling_rate, audio = input_audio
|
||||
# print(audio.shape,sampling_rate)
|
||||
duration = audio.shape[0] / sampling_rate
|
||||
if duration > 90:
|
||||
return "请上传小于90s的音频，需要转换长音频请本地进行转换", None
|
||||
audio = (audio / np.iinfo(audio.dtype).max).astype(np.float32)
|
||||
if len(audio.shape) > 1:
|
||||
audio = librosa.to_mono(audio.transpose(1, 0))
|
||||
if sampling_rate != 16000:
|
||||
audio = librosa.resample(audio, orig_sr=sampling_rate, target_sr=16000)
|
||||
print(audio.shape)
|
||||
out_wav_path = "temp.wav"
|
||||
soundfile.write(out_wav_path, audio, 16000, format="wav")
|
||||
print( cluster_ratio, auto_f0, noise_scale)
|
||||
_audio = model.slice_inference(out_wav_path, sid, vc_transform, slice_db, cluster_ratio, auto_f0, noise_scale)
|
||||
return "Success", (44100, _audio)
|
||||
|
||||
|
||||
app = gr.Blocks()
|
||||
with app:
|
||||
with gr.Tabs():
|
||||
with gr.TabItem("Basic"):
|
||||
gr.Markdown(value="""
|
||||
sovits4.0 在线demo
|
||||
|
||||
此demo为预训练底模在线demo，使用数据：云灏 即霜 辉宇·星AI 派蒙 绫地宁宁
|
||||
""")
|
||||
spks = list(model.spk2id.keys())
|
||||
sid = gr.Dropdown(label="音色", choices=spks, value=spks[0])
|
||||
vc_input3 = gr.Audio(label="上传音频（长度小于90秒）")
|
||||
vc_transform = gr.Number(label="变调（整数，可以正负，半音数量，升高八度就是12）", value=0)
|
||||
cluster_ratio = gr.Number(label="聚类模型混合比例，0-1之间，默认为0不启用聚类，能提升音色相似度，但会导致咬字下降（如果使用建议0.5左右）", value=0)
|
||||
auto_f0 = gr.Checkbox(label="自动f0预测，配合聚类模型f0预测效果更好,会导致变调功能失效（仅限转换语音，歌声不要勾选此项会究极跑调）", value=False)
|
||||
slice_db = gr.Number(label="切片阈值", value=-40)
|
||||
noise_scale = gr.Number(label="noise_scale 建议不要动，会影响音质，玄学参数", value=0.4)
|
||||
vc_submit = gr.Button("转换", variant="primary")
|
||||
vc_output1 = gr.Textbox(label="Output Message")
|
||||
vc_output2 = gr.Audio(label="Output Audio")
|
||||
vc_submit.click(vc_fn, [sid, vc_input3, vc_transform,auto_f0,cluster_ratio, slice_db, noise_scale], [vc_output1, vc_output2])
|
||||
|
||||
app.launch()
|
||||
|
||||
|
||||
|
||||
177
webUI.py
177
webUI.py
@ -9,7 +9,6 @@ import numpy as np
|
||||
import soundfile
|
||||
from inference.infer_tool import Svc
|
||||
import logging
|
||||
import traceback
|
||||
|
||||
import subprocess
|
||||
import edge_tts
|
||||
@ -27,20 +26,50 @@ logging.getLogger('multipart').setLevel(logging.WARNING)
|
||||
|
||||
model = None
|
||||
spk = None
|
||||
debug=False
|
||||
debug = False
|
||||
|
||||
cuda = []
|
||||
if torch.cuda.is_available():
|
||||
for i in range(torch.cuda.device_count()):
|
||||
cuda.append("cuda:{}".format(i))
|
||||
device_name = torch.cuda.get_device_properties(i).name
|
||||
cuda.append(f"CUDA:{i} {device_name}")
|
||||
|
||||
def modelAnalysis(model_path,config_path,cluster_model_path,device,enhance):
|
||||
global model
|
||||
try:
|
||||
model = Svc(model_path.name, config_path.name, device=device if device!="Auto" else None, cluster_model_path = cluster_model_path.name if cluster_model_path != None else "",nsf_hifigan_enhance=enhance)
|
||||
spks = list(model.spk2id.keys())
|
||||
device_name = torch.cuda.get_device_properties(model.dev).name if "cuda" in str(model.dev) else str(model.dev)
|
||||
msg = f"成功加载模型到设备{device_name}上\n"
|
||||
if cluster_model_path is None:
|
||||
msg += "未加载聚类模型\n"
|
||||
else:
|
||||
msg += f"聚类模型{cluster_model_path.name}加载成功\n"
|
||||
msg += "当前模型的可用音色：\n"
|
||||
for i in spks:
|
||||
msg += i + " "
|
||||
return sid.update(choices = spks,value=spks[0]), msg
|
||||
except Exception as e:
|
||||
raise gr.Error(e)
|
||||
|
||||
|
||||
def modelUnload():
|
||||
global model
|
||||
if model is None:
|
||||
return sid.update(choices = [],value=""),"没有模型需要卸载!"
|
||||
else:
|
||||
model = None
|
||||
torch.cuda.empty_cache()
|
||||
return sid.update(choices = [],value=""),"模型卸载完毕!"
|
||||
|
||||
|
||||
def vc_fn(sid, input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, noise_scale,pad_seconds,cl_num,lg_num,lgr_num,F0_mean_pooling,enhancer_adaptive_key):
|
||||
global model
|
||||
try:
|
||||
if input_audio is None:
|
||||
return "You need to upload an audio", None
|
||||
raise gr.Error("你需要上传音频")
|
||||
if model is None:
|
||||
return "You need to upload an model", None
|
||||
raise gr.Error("你需要指定模型")
|
||||
sampling_rate, audio = input_audio
|
||||
# print(audio.shape,sampling_rate)
|
||||
audio = (audio / np.iinfo(audio.dtype).max).astype(np.float32)
|
||||
@ -54,16 +83,16 @@ def vc_fn(sid, input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, noise
|
||||
#构建保存文件的路径，并保存到results文件夹内
|
||||
try:
|
||||
timestamp = str(int(time.time()))
|
||||
output_file = os.path.join("./results", sid + "_" + timestamp + ".wav")
|
||||
filename = sid + "_" + timestamp + ".wav"
|
||||
output_file = os.path.join("./results", filename)
|
||||
soundfile.write(output_file, _audio, model.target_sample, format="wav")
|
||||
return "Success", (model.target_sample, _audio)
|
||||
return f"推理成功，音频文件保存为results/{filename}", (model.target_sample, _audio)
|
||||
except Exception as e:
|
||||
if debug:traceback.print_exc()
|
||||
return "自动保存失败，请手动保存，音乐输出见下", (model.target_sample, _audio)
|
||||
raise gr.Error(e)
|
||||
except Exception as e:
|
||||
if debug:traceback.print_exc()
|
||||
return "异常信息:"+str(e)+"\n请排障后重试",None
|
||||
|
||||
raise gr.Error(e)
|
||||
|
||||
|
||||
def tts_func(_text,_rate):
|
||||
#使用edge-tts把文字转成音频
|
||||
# voice = "zh-CN-XiaoyiNeural"#女性，较高音
|
||||
@ -88,6 +117,7 @@ def tts_func(_text,_rate):
|
||||
p.wait()
|
||||
return output_file
|
||||
|
||||
|
||||
def vc_fn2(sid, input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, noise_scale,pad_seconds,cl_num,lg_num,lgr_num,text2tts,tts_rate,F0_mean_pooling,enhancer_adaptive_key):
|
||||
#使用edge-tts把文字转成音频
|
||||
output_file=tts_func(text2tts,tts_rate)
|
||||
@ -110,76 +140,73 @@ def vc_fn2(sid, input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, nois
|
||||
os.remove(save_path2)
|
||||
return a,b
|
||||
|
||||
app = gr.Blocks()
|
||||
with app:
|
||||
|
||||
with gr.Blocks(
|
||||
theme=gr.themes.Base(
|
||||
primary_hue = gr.themes.colors.green,
|
||||
font=["Source Sans Pro", "Arial", "sans-serif"],
|
||||
font_mono=['JetBrains mono', "Consolas", 'Courier New']
|
||||
),
|
||||
) as app:
|
||||
with gr.Tabs():
|
||||
with gr.TabItem("Sovits4.0"):
|
||||
with gr.TabItem("Inference"):
|
||||
gr.Markdown(value="""
|
||||
Sovits4.0 WebUI
|
||||
So-vits-svc 4.0 推理 webui
|
||||
""")
|
||||
|
||||
gr.Markdown(value="""
|
||||
<font size=3>下面是模型文件选择：</font>
|
||||
""")
|
||||
model_path = gr.File(label="模型文件")
|
||||
gr.Markdown(value="""
|
||||
<font size=3>下面是配置文件选择：</font>
|
||||
""")
|
||||
config_path = gr.File(label="配置文件")
|
||||
gr.Markdown(value="""
|
||||
<font size=3>下面是聚类模型文件选择，没有可以不填：</font>
|
||||
""")
|
||||
cluster_model_path = gr.File(label="聚类模型文件")
|
||||
device = gr.Dropdown(label="推理设备，默认为自动选择cpu和gpu",choices=["Auto",*cuda,"cpu"],value="Auto")
|
||||
enhance = gr.Checkbox(label="是否使用NSF_HIFIGAN增强,该选项对部分训练集少的模型有一定的音质增强效果，但是对训练好的模型有反面效果，默认关闭", value=False)
|
||||
gr.Markdown(value="""
|
||||
<font size=3>全部上传完毕后(全部文件模块显示download),点击模型解析进行解析：</font>
|
||||
""")
|
||||
model_analysis_button = gr.Button(value="模型解析")
|
||||
model_unload_button = gr.Button(value="模型卸载")
|
||||
sid = gr.Dropdown(label="音色（说话人）")
|
||||
sid_output = gr.Textbox(label="Output Message")
|
||||
with gr.Row(variant="panel"):
|
||||
with gr.Column():
|
||||
gr.Markdown(value="""
|
||||
<font size=2> 模型设置</font>
|
||||
""")
|
||||
model_path = gr.File(label="选择模型文件")
|
||||
config_path = gr.File(label="选择配置文件")
|
||||
cluster_model_path = gr.File(label="选择聚类模型文件（没有可以不选）")
|
||||
device = gr.Dropdown(label="推理设备，默认为自动选择CPU和GPU", choices=["Auto",*cuda,"CPU"], value="Auto")
|
||||
enhance = gr.Checkbox(label="是否使用NSF_HIFIGAN增强,该选项对部分训练集少的模型有一定的音质增强效果，但是对训练好的模型有反面效果，默认关闭", value=False)
|
||||
with gr.Column():
|
||||
gr.Markdown(value="""
|
||||
<font size=3>左侧文件全部选择完毕后(全部文件模块显示download)，点击“加载模型”进行解析：</font>
|
||||
""")
|
||||
model_load_button = gr.Button(value="加载模型", variant="primary")
|
||||
model_unload_button = gr.Button(value="卸载模型", variant="primary")
|
||||
sid = gr.Dropdown(label="音色（说话人）")
|
||||
sid_output = gr.Textbox(label="Output Message")
|
||||
|
||||
text2tts=gr.Textbox(label="在此输入要转译的文字。注意，使用该功能建议打开F0预测，不然会很怪")
|
||||
tts_rate = gr.Number(label="tts语速", value=0)
|
||||
|
||||
with gr.Row(variant="panel"):
|
||||
with gr.Column():
|
||||
gr.Markdown(value="""
|
||||
<font size=2> 推理设置</font>
|
||||
""")
|
||||
auto_f0 = gr.Checkbox(label="自动f0预测，配合聚类模型f0预测效果更好,会导致变调功能失效（仅限转换语音，歌声勾选此项会究极跑调）", value=False)
|
||||
F0_mean_pooling = gr.Checkbox(label="是否对F0使用均值滤波器(池化)，对部分哑音有改善。注意，启动该选项会导致推理速度下降，默认关闭", value=False)
|
||||
vc_transform = gr.Number(label="变调（整数，可以正负，半音数量，升高八度就是12）", value=0)
|
||||
cluster_ratio = gr.Number(label="聚类模型混合比例，0-1之间，0即不启用聚类。使用聚类模型能提升音色相似度，但会导致咬字下降（如果使用建议0.5左右）", value=0)
|
||||
slice_db = gr.Number(label="切片阈值", value=-40)
|
||||
noise_scale = gr.Number(label="noise_scale 建议不要动，会影响音质，玄学参数", value=0.4)
|
||||
with gr.Column():
|
||||
pad_seconds = gr.Number(label="推理音频pad秒数，由于未知原因开头结尾会有异响，pad一小段静音段后就不会出现", value=0.5)
|
||||
cl_num = gr.Number(label="音频自动切片，0为不切片，单位为秒(s)", value=0)
|
||||
lg_num = gr.Number(label="两端音频切片的交叉淡入长度，如果自动切片后出现人声不连贯可调整该数值，如果连贯建议采用默认值0，注意，该设置会影响推理速度，单位为秒/s", value=0)
|
||||
lgr_num = gr.Number(label="自动音频切片后，需要舍弃每段切片的头尾。该参数设置交叉长度保留的比例，范围0-1,左开右闭", value=0.75)
|
||||
enhancer_adaptive_key = gr.Number(label="使增强器适应更高的音域(单位为半音数)|默认为0", value=0)
|
||||
with gr.Tabs():
|
||||
with gr.TabItem("音频转音频"):
|
||||
vc_input3 = gr.Audio(label="选择音频")
|
||||
vc_submit = gr.Button("音频转换", variant="primary")
|
||||
with gr.TabItem("文字转音频"):
|
||||
text2tts=gr.Textbox(label="在此输入要转译的文字。注意，使用该功能建议打开F0预测，不然会很怪")
|
||||
tts_rate = gr.Number(label="tts语速", value=0)
|
||||
vc_submit2 = gr.Button("文字转换", variant="primary")
|
||||
with gr.Row():
|
||||
with gr.Column():
|
||||
vc_output1 = gr.Textbox(label="Output Message")
|
||||
with gr.Column():
|
||||
vc_output2 = gr.Audio(label="Output Audio", interactive=False)
|
||||
|
||||
vc_input3 = gr.Audio(label="上传音频")
|
||||
vc_transform = gr.Number(label="变调（整数，可以正负，半音数量，升高八度就是12）", value=0)
|
||||
cluster_ratio = gr.Number(label="聚类模型混合比例，0-1之间，默认为0不启用聚类，能提升音色相似度，但会导致咬字下降（如果使用建议0.5左右）", value=0)
|
||||
auto_f0 = gr.Checkbox(label="自动f0预测，配合聚类模型f0预测效果更好,会导致变调功能失效（仅限转换语音，歌声不要勾选此项会究极跑调）", value=False)
|
||||
F0_mean_pooling = gr.Checkbox(label="是否对F0使用均值滤波器(池化)，对部分哑音有改善。注意，启动该选项会导致推理速度下降，默认关闭", value=False)
|
||||
slice_db = gr.Number(label="切片阈值", value=-40)
|
||||
noise_scale = gr.Number(label="noise_scale 建议不要动，会影响音质，玄学参数", value=0.4)
|
||||
cl_num = gr.Number(label="音频自动切片，0为不切片，单位为秒/s", value=0)
|
||||
pad_seconds = gr.Number(label="推理音频pad秒数，由于未知原因开头结尾会有异响，pad一小段静音段后就不会出现", value=0.5)
|
||||
lg_num = gr.Number(label="两端音频切片的交叉淡入长度，如果自动切片后出现人声不连贯可调整该数值，如果连贯建议采用默认值0，注意，该设置会影响推理速度，单位为秒/s", value=0)
|
||||
lgr_num = gr.Number(label="自动音频切片后，需要舍弃每段切片的头尾。该参数设置交叉长度保留的比例，范围0-1,左开右闭", value=0.75,interactive=True)
|
||||
enhancer_adaptive_key = gr.Number(label="使增强器适应更高的音域(单位为半音数)|默认为0", value=0,interactive=True)
|
||||
vc_submit = gr.Button("音频直接转换", variant="primary")
|
||||
vc_submit2 = gr.Button("文字转音频+转换", variant="primary")
|
||||
vc_output1 = gr.Textbox(label="Output Message")
|
||||
vc_output2 = gr.Audio(label="Output Audio")
|
||||
def modelAnalysis(model_path,config_path,cluster_model_path,device,enhance):
|
||||
global model
|
||||
try:
|
||||
model = Svc(model_path.name, config_path.name,device=device if device!="Auto" else None,cluster_model_path= cluster_model_path.name if cluster_model_path!=None else "",nsf_hifigan_enhance=enhance)
|
||||
spks = list(model.spk2id.keys())
|
||||
device_name = torch.cuda.get_device_properties(model.dev).name if "cuda" in str(model.dev) else str(model.dev)
|
||||
return sid.update(choices = spks,value=spks[0]),"ok,模型被加载到了设备{}之上".format(device_name)
|
||||
except Exception as e:
|
||||
if debug:traceback.print_exc()
|
||||
return "","异常信息:"+str(e)+"\n请排障后重试"
|
||||
def modelUnload():
|
||||
global model
|
||||
if model is None:
|
||||
return sid.update(choices = [],value=""),"没有模型需要卸载!"
|
||||
else:
|
||||
model = None
|
||||
torch.cuda.empty_cache()
|
||||
return sid.update(choices = [],value=""),"模型卸载完毕!"
|
||||
vc_submit.click(vc_fn, [sid, vc_input3, vc_transform,auto_f0,cluster_ratio, slice_db, noise_scale,pad_seconds,cl_num,lg_num,lgr_num,F0_mean_pooling,enhancer_adaptive_key], [vc_output1, vc_output2])
|
||||
vc_submit2.click(vc_fn2, [sid, vc_input3, vc_transform,auto_f0,cluster_ratio, slice_db, noise_scale,pad_seconds,cl_num,lg_num,lgr_num,text2tts,tts_rate,F0_mean_pooling,enhancer_adaptive_key], [vc_output1, vc_output2])
|
||||
model_analysis_button.click(modelAnalysis,[model_path,config_path,cluster_model_path,device,enhance],[sid,sid_output])
|
||||
model_load_button.click(modelAnalysis,[model_path,config_path,cluster_model_path,device,enhance],[sid,sid_output])
|
||||
model_unload_button.click(modelUnload,[],[sid,sid_output])
|
||||
app.launch()
|
||||
|
||||
|
||||
Loading…
Reference in New Issue
Block a user