Update README.md

README.md

@@ -6,6 +6,7 @@ pipeline_tag: audio-to-audio
 
 <!-- Provide a quick summary of what the model is/does. -->
 
+## Abstract
 Despite recent advances in neural speech codecs, achieving high-fidelity speech reconstruction at low bitrates remains a formidable challenge. To address this limitation, we propose ESDCodec, a speech codec that integrates a thoroughly enhanced semantic quantizer and a conditioned decoder network. Specifically, we employ a randomly initialized and frozen codebook, followed by a lightweight projector, to encode semantic 
 details entirely within a linear space while enhancing codebook utilization. To further improve perceptual quality, we design a condition network 
 that injects prior subband knowledge into the upsampling decoder. Taking the de-quantized feature as input, this network predicts subband signals, 
@@ -58,7 +59,7 @@ trainer.batch_size=3 \
 data.segment_speech.segment_length=96000
 ```
 
-### Acknowledgement
+## Acknowledgement
 This repo is directly based on the following excellent projects:
 
 - [**DualCodec**](https://github.com/jiaqili3/DualCodec)