OPENGIT/Retrieval-based-Voice-Conversion-WebUI
1
0
Fork 0
mirror of https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git synced 2025-01-31 18:52:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #28 from fumiama/main

Browse Source 
fix: MacOS 纯 CPU 推理时 Segmentation fault: 11
This commit is contained in:
liujing04 2023-04-10 20:42:20 +08:00 committed by GitHub
commit adade0e225
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 52 additions and 57 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
README.md
View File

@ -1,21 +1,28 @@
# Retrieval-based-Voice-Conversion-WebUI
<div align="center">
<h1>Retrieval-based-Voice-Conversion-WebUI</h1>
一个基于VITS的简单易用的语音转换（变声器）框架<br><br>
[![madewithlove](https://forthebadge.com/images/badges/built-with-love.svg)](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI)
<img src="https://counter.seku.su/cmoe?name=rvc&theme=r34" /><br>
[![Open In Colab](https://img.shields.io/badge/Colab-F9AB00?style=for-the-badge&logo=googlecolab&color=525252)](https://colab.research.google.com/github/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)
[![Licence](https://img.shields.io/github/license/liujing04/Retrieval-based-Voice-Conversion-WebUI?style=for-the-badge)](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/%E4%BD%BF%E7%94%A8%E9%9C%80%E9%81%B5%E5%AE%88%E7%9A%84%E5%8D%8F%E8%AE%AE-LICENSE.txt)
[![Huggingface](https://img.shields.io/badge/🤗%20-Spaces-blue.svg?style=for-the-badge)](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/)
### 使用了RVC的实时语音转换 : [w-okada/voice-changer](https://github.com/w-okada/voice-changer)
------
</div>
一个基于VITS的简单易用的语音转换（变声器）框架。
------
[**更新日志**](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/Changelog_CN.md)
[**English**](./README_en.md) | [**中文简体**](./README.md)
> 点此查看我们的[演示视频](https://www.bilibili.com/video/BV1pm4y1z7Gm/) !
> 使用了RVC的实时语音转换: [w-okada/voice-changer](https://github.com/w-okada/voice-changer)
## 简介
本仓库具有以下特点:
+ 使用top1特征模型检索来杜绝音色泄漏；
@ -47,9 +54,13 @@ poetry install
```
你也可以通过pip来安装依赖：
**注意**: `MacOS`下`faiss 1.7.2`版本会导致抛出段错误，请将`requirements.txt`的对应条目改为`faiss-cpu==1.7.0`
```bash
pip install -r requirements.txt
```
## 其他预模型准备
RVC需要其他的一些预模型来推理和训练。

3
README_en.md
View File

@ -40,9 +40,12 @@ poetry install
```
You can also use pip to install the dependencies
**Notice**: `faiss 1.7.2` will raise Segmentation Fault: 11 under `MacOS`, please change corresponding line in `requirements.txt` to `faiss-cpu==1.7.0`
```bash
pip install -r requirements.txt
```
## Preparation of other Pre-models
RVC requires other pre-models to infer and train.

32
README_v0.md
View File

@ -1,32 +0,0 @@
# Retrieval-based-Voice-Conversion-WebUI
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)
缺失的2个文件夹和2个文件：
hubert_base.pt
ffmpeg（自己确保ffmpeg命令能执行就行）
pretrained文件夹
uvr5_weights文件夹
文件太大github传不动，去huggingface上下https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main
当然你也可以直接看看RVC-beta.7z这个文件→_→
按照requirements.txt用pip装好环境，python infer-web.py就能用了
根据经验，librosa numpy和numba三个包最好写死版本否则容易有坑，其他的包版本不太重要
宣传视频：https://www.bilibili.com/video/BV1pm4y1z7Gm/
教程见小白简易教程.doc
We will develop an English version windows WebUI APP in 2 weeks.
### Realtime Voice Conversion Software using RVC
https://github.com/w-okada/voice-changer

31
Retrieval_based_Voice_Conversion_WebUI.ipynb
View File

@ -129,10 +129,10 @@
"#@title 从谷歌云盘加载打包好的数据集到/content/dataset\n",
"\n",
"#@markdown 数据集位置\n",
"DATASET = \"/content/drive/MyDrive/dataset/lulucall_48k.zip\" #@param {type:\"string\"}\n",
"DATASET = \"/content/drive/MyDrive/dataset/lulu20230327_32k.zip\" #@param {type:\"string\"}\n",
"\n",
"!mkdir -p /content/dataset\n",
"!unzip -d /content/dataset {DATASET}"
"!unzip -d /content/dataset -B {DATASET}"
],
"metadata": {
"id": "Mwk7Q0Loqzjx"
@ -140,13 +140,26 @@
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"#@title 重命名数据集中的重名文件\n",
"!ls -a /content/dataset/\n",
"!rename 's/(\\w+)\\.(\\w+)~(\\d*)/$1_$3.$2/' /content/dataset/*.*~*"
],
"metadata": {
"id": "PDlFxWHWEynD"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"#@title 启动web\n",
"%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
"%load_ext tensorboard\n",
"%tensorboard --logdir /content/Retrieval-based-Voice-Conversion-WebUI/logs\n",
"# %load_ext tensorboard\n",
"# %tensorboard --logdir /content/Retrieval-based-Voice-Conversion-WebUI/logs\n",
"!python3 infer-web.py --colab --pycmd python3"
],
"metadata": {
@ -164,7 +177,7 @@
"#@markdown 模型名\n",
"MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
"#@markdown 模型epoch\n",
"MODELEPOCH = 7500 #@param {type:\"integer\"}\n",
"MODELEPOCH = 9600 #@param {type:\"integer\"}\n",
"\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth\n",
@ -188,7 +201,7 @@
"#@markdown 模型名\n",
"MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
"#@markdown 模型epoch\n",
"MODELEPOCH = 6000 #@param {type:\"integer\"}\n",
"MODELEPOCH = 7500 #@param {type:\"integer\"}\n",
"\n",
"!mkdir -p /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
"\n",
@ -241,7 +254,7 @@
"#@markdown 模型名\n",
"MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
"#@markdown 停止的epoch\n",
"MODELEPOCH = 2500 #@param {type:\"integer\"}\n",
"MODELEPOCH = 3200 #@param {type:\"integer\"}\n",
"#@markdown 保存epoch间隔\n",
"EPOCHSAVE = 100 #@param {type:\"integer\"}\n",
"#@markdown 采样率\n",
@ -262,7 +275,7 @@
"#@markdown 模型名\n",
"MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
"#@markdown 选中模型epoch\n",
"MODELEPOCH = 7700 #@param {type:\"integer\"}\n",
"MODELEPOCH = 9600 #@param {type:\"integer\"}\n",
"\n",
"!echo \"备份选中的模型。。。\"\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
@ -292,7 +305,7 @@
"#@markdown 模型名\n",
"MODELNAME = \"lulu\" #@param {type:\"string\"}\n",
"#@markdown 选中模型epoch\n",
"MODELEPOCH = 7700 #@param {type:\"integer\"}\n",
"MODELEPOCH = 9600 #@param {type:\"integer\"}\n",
"\n",
"!echo \"备份选中的模型。。。\"\n",
"!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",

10
infer-web.py
View File

@ -9,7 +9,7 @@ import faiss
ncpu=cpu_count()
ngpu=torch.cuda.device_count()
gpu_infos=[]
if(torch.cuda.is_available()==False or ngpu==0):if_gpu_ok=False
if((not torch.cuda.is_available()) or ngpu==0):if_gpu_ok=False
else:
if_gpu_ok = False
for i in range(ngpu):
@ -79,7 +79,7 @@ def vc_single(sid,input_audio,f0_up_key,f0_file,f0_method,file_index,file_big_np
if(hubert_model==None):load_hubert()
if_f0 = cpt.get("f0", 1)
audio_opt=vc.pipeline(hubert_model,net_g,sid,audio,times,f0_up_key,f0_method,file_index,file_big_npy,index_rate,if_f0,f0_file=f0_file)
print(times)
print("npy: ", times[0], "s, f0:", times[1], "s, infer: ", times[2], "s", sep='')
return "Success", (tgt_sr, audio_opt)
except:
info=traceback.format_exc()
@ -140,7 +140,7 @@ def uvr(model_name,inp_root,save_root_vocal,paths,save_root_ins):
except:
traceback.print_exc()
print("clean_empty_cache")
torch.cuda.empty_cache()
if torch.cuda.is_available(): torch.cuda.empty_cache()
yield "\n".join(infos)
#一个选项卡全局只能有一个音色
@ -152,7 +152,7 @@ def get_vc(sid):
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
torch.cuda.empty_cache()
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)
if (if_f0 == 1):
@ -160,7 +160,7 @@ def get_vc(sid):
else:
net_g = SynthesizerTrnMs256NSFsid_nono(*cpt["config"])
del net_g,cpt
torch.cuda.empty_cache()
if torch.cuda.is_available(): torch.cuda.empty_cache()
cpt=None
return {"visible": False, "__type__": "update"}
person = "%s/%s" % (weight_root, sid)

8
infer/infer-pm-index256.py
View File

@ -104,7 +104,7 @@ for idx,name in enumerate(["冬之花clip1.wav",]):##
"padding_mask": padding_mask.to(device),
"output_layer": 9, # layer 9
}
torch.cuda.synchronize()
if torch.cuda.is_available(): torch.cuda.synchronize()
t0=ttime()
with torch.no_grad():
logits = model.extract_features(**inputs)
@ -116,13 +116,13 @@ for idx,name in enumerate(["冬之花clip1.wav",]):##
feats = torch.from_numpy(big_npy[I.squeeze()].astype("float16")).unsqueeze(0).to(device)
feats=F.interpolate(feats.permute(0,2,1),scale_factor=2).permute(0,2,1)
torch.cuda.synchronize()
if torch.cuda.is_available(): torch.cuda.synchronize()
t1=ttime()
# p_len = min(feats.shape[1],10000,pitch.shape[0])#太大了爆显存
p_len = min(feats.shape[1],10000)#
pitch, pitchf = get_f0(audio, p_len,f0_up_key)
p_len = min(feats.shape[1],10000,pitch.shape[0])#太大了爆显存
torch.cuda.synchronize()
if torch.cuda.is_available(): torch.cuda.synchronize()
t2=ttime()
feats = feats[:,:p_len, :]
pitch = pitch[:p_len]
@ -133,7 +133,7 @@ for idx,name in enumerate(["冬之花clip1.wav",]):##
pitchf = torch.FloatTensor(pitchf).unsqueeze(0).to(device)
with torch.no_grad():
audio = net_g.infer(feats, p_len,pitch,pitchf,sid)[0][0, 0].data.cpu().float().numpy()#nsf
torch.cuda.synchronize()
if torch.cuda.is_available(): torch.cuda.synchronize()
t3=ttime()
ta0+=(t1-t0)
ta1+=(t2-t1)

6
vc_infer_pipeline.py
View File

@ -79,7 +79,7 @@ class VC(object):
if(isinstance(index,type(None))==False and isinstance(big_npy,type(None))==False and index_rate!=0):
npy = feats[0].cpu().numpy()
if(self.is_half==True):npy=npy.astype("float32")
D, I = index.search(npy, 1)
_, I = index.search(npy, 1)
npy=big_npy[I.squeeze()]
if(self.is_half==True):npy=npy.astype("float16")
feats = torch.from_numpy(npy).unsqueeze(0).to(self.device)*index_rate + (1-index_rate)*feats
@ -99,7 +99,7 @@ class VC(object):
else:
audio1 = (net_g.infer(feats, p_len, sid)[0][0, 0] * 32768).data.cpu().float().numpy().astype(np.int16)
del feats,p_len,padding_mask
torch.cuda.empty_cache()
if torch.cuda.is_available(): torch.cuda.empty_cache()
t2 = ttime()
times[0] += (t1 - t0)
times[2] += (t2 - t1)
@ -160,5 +160,5 @@ class VC(object):
audio_opt.append(self.vc(model,net_g,sid,audio_pad[t:],None,None,times,index,big_npy,index_rate)[self.t_pad_tgt:-self.t_pad_tgt])
audio_opt=np.concatenate(audio_opt)
del pitch,pitchf,sid
torch.cuda.empty_cache()
if torch.cuda.is_available(): torch.cuda.empty_cache()
return audio_opt