update readme for vits.

README.md

@@ -476,7 +476,7 @@ PaddleSpeech supports a series of most popular models. They are summarized in [r
       </td>
     </tr>
     <tr>
-      <td rowspan="3">Voice Cloning</td>
+      <td rowspan="4">Voice Cloning</td>
       <td>GE2E</td>
       <td >Librispeech, etc.</td>
       <td>
@@ -496,6 +496,13 @@ PaddleSpeech supports a series of most popular models. They are summarized in [r
       <td>
       <a href = "./examples/aishell3/vc1">ge2e-fastspeech2-aishell3</a>
       </td>
+    </tr>
+    <tr>
+      <td>GE2E + VITS</td>
+      <td>AISHELL-3</td>
+      <td>
+      <a href = "./examples/aishell3/vits-vc">ge2e-vits-aishell3</a>
+      </td>
     </tr>
      <tr>
       <td rowspan="3">End-to-End</td>

README_cn.md

@@ -601,7 +601,7 @@ PaddleSpeech 的 **语音合成** 主要包含三个模块：文本前端、声
       </td>
     </tr>
     <tr>
-      <td rowspan="3">声音克隆</td>
+      <td rowspan="4">声音克隆</td>
       <td>GE2E</td>
       <td >Librispeech, etc.</td>
       <td>
@@ -622,13 +622,20 @@ PaddleSpeech 的 **语音合成** 主要包含三个模块：文本前端、声
       <a href = "./examples/aishell3/vc1">ge2e-fastspeech2-aishell3</a>
       </td>
     </tr>
+    <tr>
+      <td>GE2E + VITS</td>
+      <td>AISHELL-3</td>
+      <td>
+      <a href = "./examples/aishell3/vits-vc">ge2e-vits-aishell3</a>
+      </td>
+    </tr>
     </tr>
      <tr>
       <td rowspan="3">端到端</td>
       <td>VITS</td>
-      <td >CSMSC</td>
+      <td>CSMSC / AISHELL-3</td>
       <td>
-      <a href = "./examples/csmsc/vits">VITS-csmsc</a>
+      <a href = "./examples/csmsc/vits">VITS-csmsc</a> / <a href = "./examples/aishell3/vits">VITS-aishell3</a>
       </td>
     </tr>
   </tbody>

examples/aishell3/vits-vc/README.md

@@ -131,6 +131,8 @@ If you want to convert a speaker audio file to refered speaker, run:
 CUDA_VISIBLE_DEVICES=${gpus} ./local/voice_cloning.sh ${conf_path} ${train_output_path} ${ckpt_name} ${ge2e_params_path} ${add_blank} ${ref_audio_dir} ${src_audio_path}
 ```
 
+<!-- TODO display these after we trained the model -->
+<!-- 
 ## Pretrained Model
 
 The pretrained model can be downloaded here:
@@ -148,3 +150,4 @@ vits_vc_aishell3_ckpt_1.1.0
 ```
 
 ps: This ckpt is not good enough, a better result is training
+-->

examples/aishell3/vits/README.md

@@ -163,6 +163,8 @@ optional arguments:
 5. `--output_dir` is the directory to save synthesized audio files.
 6. `--ngpu` is the number of gpus to use, if ngpu == 0, use cpu.
 
+<!-- TODO display these after we trained the model -->
+<!-- 
 ## Pretrained Model
 
 The pretrained model can be downloaded here:
@@ -197,3 +199,4 @@ python3 ${BIN_DIR}/synthesize_e2e.py \
     --text=${BIN_DIR}/../sentences.txt \
     --add-blank=${add_blank} 
 ```
+-->