Fix: Define missing audio input and required imports in example code

README.md

@@ -9,6 +9,8 @@ This repo brings fairseq ContentVec model to HuggingFace Transformers.
 ## How to use
 To use this model, you need to define
 ```python
+from transformers import HubertModel
+import torch.nn as nn
 class HubertModelWithFinalProj(HubertModel):
     def __init__(self, config):
         super().__init__(config)
@@ -21,6 +23,8 @@ class HubertModelWithFinalProj(HubertModel):
 
 and then load the model with
 ```python
+audio = torch.randn(1, 16000)
+
 model = HubertModelWithFinalProj.from_pretrained("lengyue233/content-vec-best")
 
 x = model(audio)["last_hidden_state"]