Update README.md

README.md

@@ -1,8 +1,8 @@
----
-license: cc-by-4.0
-language:
-- en
----
+---
+license: cc-by-4.0
+language:
+- en
+---
 ## Linacodec: Highly compressive audio tokenizer for speech models.
 <p align="center">
   <a href="https://huggingface.co/YatharthS/LinaCodec">
@@ -20,7 +20,7 @@ Linacodec is an audio tokenizer that compresses audio into just 12.5 tokens per
 * Many Tasks: Indirectly even supports voice conversion, audio super-resolution, and audio denoising!
 
 ### Why is this even useful?
-Audio tokenizers directly contribute to speed, quality, and capability. LinaCodec massively improves upon previous codecs.
+Audio tokenizers directly contribute to speed, quality, and capability of TTS/ASR models. LinaCodec massively improves upon previous codecs in these areas.
 * Inference Speed: Enables TTS models to run 800x realtime, 8x faster than [MiraTTS](https://github.com/ysharma3501)!
 * Fast training: High-quality TTS models can be trained in less then 1 day.
 * Versatile: Works for both Text-to-Speech and Speech-to-Text unlike most other codecs.