Update README.md

README.md

@@ -1,12 +1,12 @@
 ---
 license: mit
+language:
+- en
 ---
 
-# Amphion Text-to-Speech Pretrained Models
+# Pretrained Model of Amphion VITS
 
-We provide the following pretrained checkpoints for you to use, specifically:
-
-A [VITS](https://github.com/open-mmlab/Amphion/tree/main/egs/tts/VITS) pretrained checkpoint trained on LJSpeech, which consists of 13,100 short audio clips of a single speaker and have a total length of approximately 24 hours.
+We provide the pre-trained checkpoint of [VITS](https://github.com/open-mmlab/Amphion/tree/main/egs/tts/VITS) trained on LJSpeech, which consists of 13,100 short audio clips of a single speaker and have a total length of approximately 24 hours.
 
 
 
@@ -45,5 +45,4 @@ sh egs/tts/VITS/run.sh --stage 3 --gpu "0" \
 	--infer_output_dir ckpts/tts/vits-ljspeech/result \
 	--infer_mode "single" \
     --infer_text "This is a clip of generated speech with the given text from a TTS model."
-```
-
+```