Update README.md

README.md

@@ -6,7 +6,16 @@ language:
 - zh
 ---
 # VALL-E
-We provide the pre-trained checkpoint of [Vall-E](https://arxiv.org/abs/2301.02111) trained on WenetSpeech4TTS.
+Pre-trained checkpoint of [Vall-E](https://arxiv.org/abs/2301.02111) with AudioDec trained on WenetSpeech4TTS.
+
+
+
+## Checkpoints
+We provide three checkpoints trained/fine-tuned on different subset of WenetSpeech4TTS.
+
+VALL-E Basic :VALL-E trained with the WenetSpeech4TTS Basic subset
+VALL-E Standard: VALL-E Basic fine-tuning with the WenetSpeech4TTS Standard subset
+VALL-E Premium: VALL-E Standard fine-tuning with the WenetSpeech4TTS Premium subset
 
 ## Useage 
 Inference Code: [dukGuo/valle-audiodec](https://github.com/dukGuo/valle-audiodec).