Merge branch '4.1-Stable' of https://github.com/svc-develop-team/so-vits-svc into 4.1-Stable

README.md

@@ -87,6 +87,19 @@ wget -P pretrain/ http://obs.cstcloud.cn/share/obs/sankagenkeshi/checkpoint_best
 - soft vc hubert：[hubert-soft-0d54a1f4.pt](https://github.com/bshall/hubert/releases/download/v0.1/hubert-soft-0d54a1f4.pt)
   - Place it under the `pretrain` directory
 
+##### **3. If OnnxHubert/ContentVec as the encoder**
+- download model at https://huggingface.co/NaruseMioShirakana/MoeSS-SUBModel/tree/main
+  - Place it under the `pretrain` directory
+
+#### **List of Encoders**
+- "vec768l12"
+- "vec256l9"
+- "vec256l9-onnx"
+- "vec256l12-onnx"
+- "vec768l9-onnx"
+- "vec768l12-onnx"
+- "hubertsoft-onnx"
+- "hubertsoft"
 
 #### **Optional(Strongly recommend)**
 

README_zh_CN.md

@@ -84,6 +84,20 @@ wget -P pretrain/ http://obs.cstcloud.cn/share/obs/sankagenkeshi/checkpoint_best
 + soft vc hubert：[hubert-soft-0d54a1f4.pt](https://github.com/bshall/hubert/releases/download/v0.1/hubert-soft-0d54a1f4.pt)
   + 放在`pretrain`目录下
 
+##### **3. 若使用OnnxHubert/ContentVec作为声音编码器**
+- download model at https://huggingface.co/NaruseMioShirakana/MoeSS-SUBModel/tree/main
+  - Place it under the `pretrain` directory
+
+#### **编码器列表**
+- "vec768l12"
+- "vec256l9"
+- "vec256l9-onnx"
+- "vec256l12-onnx"
+- "vec768l9-onnx"
+- "vec768l12-onnx"
+- "hubertsoft-onnx"
+- "hubertsoft"
+
 #### **可选项(强烈建议使用)**
 
 + 预训练底模文件： `G_0.pth` `D_0.pth`

requirements_onnx_encoder.txt

@@ -14,7 +14,7 @@ praat-parselmouth
 onnx
 onnxsim
 onnxoptimizer
-onnxruntime
+onnxruntime-gpu
 librosa==0.9.1
 tensorboard
 tensorboardX

utils.py

@@ -108,6 +108,21 @@ def get_speech_encoder(speech_encoder,device=None,**kargs):
     elif speech_encoder == "vec256l9":
         from vencoder.ContentVec256L9 import ContentVec256L9
         speech_encoder_object = ContentVec256L9(device = device)
+    elif speech_encoder == "vec256l9-onnx":
+        from vencoder.ContentVec256L9_Onnx import ContentVec256L9_Onnx
+        speech_encoder_object = ContentVec256L9(device = device)
+    elif speech_encoder == "vec256l12-onnx":
+        from vencoder.ContentVec256L12_Onnx import ContentVec256L12_Onnx
+        speech_encoder_object = ContentVec256L9(device = device)
+    elif speech_encoder == "vec768l9-onnx":
+        from vencoder.ContentVec768L9_Onnx import ContentVec768L9_Onnx
+        speech_encoder_object = ContentVec256L9(device = device)
+    elif speech_encoder == "vec768l12-onnx":
+        from vencoder.ContentVec768L12_Onnx import ContentVec768L12_Onnx
+        speech_encoder_object = ContentVec256L9(device = device)
+    elif speech_encoder == "hubertsoft-onnx":
+        from vencoder.HubertSoft_Onnx import HubertSoft_Onnx
+        speech_encoder_object = HubertSoft(device = device)
     elif speech_encoder == "hubertsoft":
         from vencoder.HubertSoft import HubertSoft
         speech_encoder_object = HubertSoft(device = device)