add link to whisper

qdrant-landing/content/blog/case-study-dailymotion.md

@@ -65,7 +65,7 @@ By now it was clear to the Dailymotion team that the future initiatives will inv
 The solution involved implementing a content based Recommendation System leveraging Qdrant to power the similar videos, with the following characteristics.
 
 **Fields used to represent each video**  -  
-Title , Tags , Description , Transcript (generated by openAI whisper)
+Title , Tags , Description , Transcript (generated by [OpenAI whisper](https://openai.com/research/whisper))
 
 **Encoding Model used** - [MUSE - Multilingual Universal Sentence Encoder](https://www.tensorflow.org/hub/tutorials/retrieval_with_tf_hub_universal_encoder_qa)
 
@@ -159,7 +159,7 @@ The new recommender system implementation leveraging Qdrant along with the colla
 ### Outlook / Future plans
 
 The team is very excited with the results they achieved on their recommender system and wishes to continue building with it. \
-They aim to work on Perspective feed next and say  \
+They aim to work on Perspective feed next and say
 
 >We've recently integrated this new recommendation system into our mobile app through a feature called Perspective. The aim of this feature is to disrupt the vertical feed algorithm, allowing users to discover new videos. When browsing their feed, users may encounter a video discussing a particular movie. With Perspective, they have the option to explore different viewpoints on the same topic. Qdrant plays a crucial role in this feature by generating candidate videos related to the subject, ensuring users are exposed to diverse perspectives and preventing them from being confined to an echo chamber where they only encounter similar viewpoints. \
 > Gladys Roch - Machine Learning Engineer