Updated README.md

README.md

@@ -15,7 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # binarization-segformer-b3
 
-This model is a fine-tuned version of [nvidia/segformer-b3](https://huggingface.co/nvidia/segformer-b3-finetuned-cityscapes-1024-1024) on the same ensemble of 13 datasets as the [SauvolaNet work](https://arxiv.org/pdf/2105.05521.pdf). The ensemble is publicly available in the official [SauvolaNet repository](https://github.com/Leedeng/SauvolaNet#datasets).
+This model is a fine-tuned version of [nvidia/segformer-b3](https://huggingface.co/nvidia/segformer-b3-finetuned-cityscapes-1024-1024) 
+on the same ensemble of 13 datasets as the [SauvolaNet](https://arxiv.org/pdf/2105.05521.pdf) work publicly available 
+in their GitHub [repository](https://github.com/Leedeng/SauvolaNet#datasets).
 
 It achieves the following results on the evaluation set on DIBCO metrics:
 - loss: 0.1017
@@ -24,18 +26,18 @@ It achieves the following results on the evaluation set on DIBCO metrics:
 - PSNR: 14.5040
 - DRD: 5.3749
 
-where PSNR stands for peak signal-to-noise ratio and DND for distance reciprocal distortion.
+with PSNR the peak signal-to-noise ratio and DND the distance reciprocal distortion.
 
 For more information on the above DIBCO metrics, see the 2017 introductory [paper](https://ieeexplore.ieee.org/document/8270159).
 
-**Warning:** This model only accepts images with a resolution of 640 due to compute constraints on Colab free tier during training.
+**Warning:** This model only accepts images with a resolution of 640 due to GPU compute constraints on Colab free tier during training.
 
 ## Model description
 
 This model is part of on-going research on pure semantic segmentation models as a formulation of document image binarization (DIBCO).
 This is in contrast to the late trend of adapting classic binarization algorithms with neural networks, 
 such as [DeepOtsu](https://arxiv.org/abs/1901.06081) or the aforementioned SauvolaNet work, 
-as extensions of the classical Otsu's method and Sauvola thresholding, respectively.
+as extensions of the classical Otsu's method and Sauvola thresholding algorithm, respectively.
 
 ## Intended uses & limitations