Update README.md

README.md

@@ -66,7 +66,7 @@ This interactive demo showcases the model's capability to effectively retrieve v
 ## Evaluations
 
 To evaluate the model's performance we used the last last 10,000 video clips and their accompanying text from the Webvid dataset.
-We evaluate R1,R5,R10,MedianR and MeanR on:
+We evaluate R1, R5, R10, MedianR, and MeanR on:
 1. Zero-shot pretrained clip-vit-base-patch32 model
 2. CLIP4Clip based weights trained on the dataset [MSR-VTT](https://paperswithcode.com/dataset/msr-vtt), consisting of 10,000 video-text pairs
 3. CLIP4Clip based weights trained on a 150K subset of the dataset Webvid-2M
@@ -84,7 +84,7 @@ For an elaborate description of the evaluation refer to the notebook
 [GSI_VideoRetrieval-Evaluation](https://huggingface.co/Diangle/clip4clip-webvid/blob/main/Notebooks/GSI_VideoRetrieval-Evaluation.ipynb).
 
 <div id="footnote1">
-<p>[1] For overall search acceleration capabilities, in order to boost you search application, please refer to searchium.ai</p>
+<p>[1] For overall search acceleration capabilities, in order to boost you search application, please refer to [Searchium.ai](https://www.searchium.ai)</p>
 </div>