Nofated095
/
so-vits-svc
mirror of https://github.com/svc-develop-team/so-vits-svc.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branch '4.0' of https://github.com/svc-develop-team/so-vits-svc into 4.0

This commit is contained in:
ylzz1997 2023-04-14 16:17:20 +08:00
parent 279f89b047 d20461d247
commit ffe4800aaf
4 changed files with 27 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -205,7 +205,9 @@ Introduction: The mean filtering of F0 can effectively reduce the hoarse sound c
### [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1kv-3y2DmZo0uya8pEr1xk7cSB-4e_Pct?usp=sharing) [sovits4_for_colab.ipynb](https://colab.research.google.com/drive/1kv-3y2DmZo0uya8pEr1xk7cSB-4e_Pct?usp=sharing)
#### [23/03/16] No longer need to download hubert manually
**[23/03/16] No longer need to download hubert manually**
**[23/04/14] Support NSF_HIFIGAN enhancer**
## 📤 Exporting to Onnx

4
README_zh_CN.md
View File

@ -205,7 +205,9 @@ python inference_main.py -m "logs/44k/G_30400.pth" -c "configs/config.json" -n "
### [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1kv-3y2DmZo0uya8pEr1xk7cSB-4e_Pct?usp=sharing) [sovits4_for_colab.ipynb](https://colab.research.google.com/drive/1kv-3y2DmZo0uya8pEr1xk7cSB-4e_Pct?usp=sharing)
#### [23/03/16] 不再需要手动下载hubert
**[23/03/16] 不再需要手动下载hubert**
**[23/04/14] 支持NSF_HIFIGAN增强器**
## 📤 Onnx导出

2
inference_main.py
View File

@ -31,7 +31,7 @@ def main():
parser.add_argument('-s', '--spk_list', type=str, nargs='+', default=['nen'], help='合成目标说话人名称')
# 可选项部分
parser.add_argument('-a', '--auto_predict_f0', action='store_true', default=False,help='语音转换自动预测音高，转换歌声时不要打开这个会严重跑调')
parser.add_argument('-a', '--auto_predict_f0', type=bool, default=False, help='语音转换自动预测音高，转换歌声时不要打开这个会严重跑调')
parser.add_argument('-cm', '--cluster_model_path', type=str, default="logs/44k/kmeans_10000.pt", help='聚类模型路径，如果没有训练聚类则随便填')
parser.add_argument('-cr', '--cluster_infer_ratio', type=float, default=0, help='聚类方案占比，范围0-1，若没有训练聚类模型则默认0即可')
parser.add_argument('-lg', '--linear_gradient', type=float, default=0, help='两段音频切片的交叉淡入长度，如果强制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，单位为秒')

23
webUI.py
View File

@ -99,11 +99,12 @@ def vc_fn(sid, input_audio, vc_transform, auto_f0,cluster_ratio, slice_db, noise
raise gr.Error(e)
def tts_func(_text,_rate):
def tts_func(_text,_rate,_voice):
#使用edge-tts把文字转成音频
# voice = "zh-CN-XiaoyiNeural"#女性，较高音
# voice = "zh-CN-YunxiNeural"#男性
voice = "zh-CN-YunxiNeural"#男性
if ( _voice == "女" ) : voice = "zh-CN-XiaoyiNeural"
output_file = _text[0:10]+".wav"
# communicate = edge_tts.Communicate(_text, voice)
# await communicate.save(output_file)
@ -112,21 +113,24 @@ def tts_func(_text,_rate):
elif _rate<0:
ratestr="{:.0%}".format(_rate)#减号自带
p=subprocess.Popen(["edge-tts",
"--text",_text,
"--write-media",output_file,
"--voice",voice,
"--rate="+ratestr]
p=subprocess.Popen("edge-tts "+
" --text "+_text+
" --write-media "+output_file+
" --voice "+voice+
" --rate="+ratestr
,shell=True,
stdout=subprocess.PIPE,
stdin=subprocess.PIPE)
p.wait()
return output_file
def text_clear(text):
return re.sub(r"[\n\,\(\) ]", "", text)
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):
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,tts_voice,F0_mean_pooling,enhancer_adaptive_key):
#使用edge-tts把文字转成音频
output_file=tts_func(text2tts,tts_rate)
text2tts=text_clear(text2tts)
output_file=tts_func(text2tts,tts_rate,tts_voice)
#调整采样率
sr2=44100
@ -206,6 +210,7 @@ with gr.Blocks(
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)
tts_voice = gr.Radio(label="性别",choices=["男","女"], value="男")
vc_submit2 = gr.Button("文字转换", variant="primary")
with gr.Row():
with gr.Column():
@ -219,7 +224,7 @@ with gr.Blocks(
""")
debug_button = gr.Checkbox(label="Debug模式，如果向社区反馈BUG需要打开，打开后控制台可以显示具体错误提示", value=debug)
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])
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,tts_voice,F0_mean_pooling,enhancer_adaptive_key], [vc_output1, vc_output2])
debug_button.change(debug_change,[],[])
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])