Update README.md

README.md

@@ -27,8 +27,7 @@ Huge Thanks to [Johnathan Duering](https://github.com/duerig) for his help. I mo
 There are Three checkpoints so far in this repository:
   - HiFormer 24khz (trained for roughly 117K~ steps on LibriTTS (360 + 100) and 40 hours of other English datasets.)
   - HiFormer 44.1khz (trained for roughly 280K~ steps on a Large (more than 1100 hours) private Multilingual dataset, covering Arabic, Persian, Japanese, English, Russian and also Singing voice in Chinese and Japanese with Quranic recitations in Arabic.
-  - HiFTNet 44.1khz (trained for ~100K steps, on a similar dataset to HiFormer 44.1khz, but slightly smaller and no singing voice.) to use this Checkpoint you should head to the [HiFTNet's repository](https://github.com/yl4579/HiFTNet). make sure your mel-preprocessing matches that of [StyleTTS](https://github.com/yl4579/StyleTTS/blob/main/meldataset.py#L60-L68).
-## Pre-requisites
+  - HiFTNet 44.1khz (trained for ~100K steps, on a similar dataset to HiFormer 44.1khz, but slightly smaller and no singing voice). 
 1. Python >= 3.10
 2. Clone this repository:
 ```bash