update hifigan readme, test=doc_fix

README.md

+
 ([简体中文](./README_cn.md)|English)
 
 <p align="center">
@@ -309,7 +310,7 @@ PaddleSpeech supports a series of most popular models. They are summarized in [r
       </td>
     </tr>
    <tr>
-      <td rowspan="3">Vocoder</td>
+      <td rowspan="5">Vocoder</td>
       <td >WaveFlow</td>
       <td >LJSpeech</td>
       <td>
@@ -329,7 +330,21 @@ PaddleSpeech supports a series of most popular models. They are summarized in [r
       <td>
       <a href = "./examples/csmsc/voc3">Multi Band MelGAN-csmsc</a> 
       </td>
-    </tr>                                                                                                                                           
+    </tr> 
+    <tr>
+      <td >Style MelGAN</td>
+      <td >CSMSC</td>
+      <td>
+      <a href = "./examples/csmsc/voc4">Style MelGAN-csmsc</a> 
+      </td>
+    </tr>
+    <tr>
+      <td >HiFiGAN</td>
+      <td >CSMSC</td>
+      <td>
+      <a href = "./examples/csmsc/voc5">HiFiGAN-csmsc</a> 
+      </td>
+    <tr>                                                                                                                                       
     <tr>
       <td rowspan="3">Voice Cloning</td>
       <td>GE2E</td>

README_cn.md

@@ -303,7 +303,7 @@ 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">声码器</td>
+      <td rowspan="5">声码器</td>
       <td >WaveFlow</td>
       <td >LJSpeech</td>
       <td>
@@ -323,7 +323,21 @@ PaddleSpeech 的 **语音合成** 主要包含三个模块：文本前端、声
       <td>
       <a href = "./examples/csmsc/voc3">Multi Band MelGAN-csmsc</a> 
       </td>
-    </tr>                                                                                                                                           
+    </tr>
+    <tr>
+      <td >Style MelGAN</td>
+      <td >CSMSC</td>
+      <td>
+      <a href = "./examples/csmsc/voc4">Style MelGAN-csmsc</a> 
+      </td>
+    </tr>
+    <tr>
+      <td >HiFiGAN</td>
+      <td >CSMSC</td>
+      <td>
+      <a href = "./examples/csmsc/voc5">HiFiGAN-csmsc</a> 
+      </td>
+    <tr>                                                                                                                                       
     <tr>
       <td rowspan="3">声音克隆</td>
       <td>GE2E</td>

examples/csmsc/voc5/README.md

@@ -117,7 +117,7 @@ optional arguments:
 ## Pretrained Models
 The pretrained model can be downloaded here [hifigan_csmsc_ckpt_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_csmsc_ckpt_0.1.1.zip).
 
-The static model can be downloaded here [hifigan_csmsc_static_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_csmsc_static_0.1.1.zip)
+The static model can be downloaded here [hifigan_csmsc_static_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_csmsc_static_0.1.1.zip).
 
 Model | Step | eval/generator_loss | eval/mel_loss| eval/feature_matching_loss
 :-------------:| :------------:| :-----: | :-----: | :--------: