Roman Engeler

We all understand what Cohere Generate and Classify do. But embed ...?! Introducing ... Cohere Analyze. You can upload any csv file. You then have 3 options. EDA gives you an overview of the data and you can get some general exploratory data analysis. Cluster, allows you to do some group analysis, with keywords generated from the body of the text and using the titles. And finally, Search, allows you to query the data and retrieve the closest match. This has significant business value because now you can gain business insights using cluster that are non-trivial. You can search a knowledge-base or other internal data sources for information. Cohere Analyze is what we have all been waiting for, to better utilize Embed.

According to research made by J. Birulés-Muntané1 and S. Soto-Faraco (10.1371/journal.pone.0158409), watching movies with subtitles can help us learn a new language more effectively. However, the traditional way of showing subtitles in YouTube or Netflix does not provide us the best way to check the meaning of new vocabulary nor understand complex slang and abbreviation. Therefore, we found out that if we display dual subtitles (the original subtitle of the video and the translated one), the learning curve immediately improves. In research conducted in Japan, the authors concluded that the participants who viewed the episode with dual subtitles did significantly better (http://callej.org/journal/22-3/Dizon-Thanyawatpokin2021.pdf). After understanding both the problem and the solution, we decided to create a platform for learning new languages with dual active transcripts. When you enter a YouTube URL or upload an MP4 file in our web application, the app will produce a web page where you can view the video and have a transcript running next to it in two different languages. We have accomplished this goal and successfully integrated OpenAI Whisper, GPT and Facebook's language model for the backend of the app. At first, we use Streamlit for the app, but it does not provide a transcript that automatically move with the audio timeline, also Streamlit does not give us the ability to design the user interface, so we create our own full stack application using Bootstrap, Flask, HTML, CSS and Javascript. Our business model is subscription-based and/or one-time purchase based on the usage. Our app isn’t just for language learners. It can also be used for writers, singers, YouTubers, or anyone who would like to make their content reach out to more people by adding different languages to their videos/audios. Due to the limitation of free hosting plan, we could not deploy the app on cloud for now but we have a simple website that you can have a quick look at what we are creating (https://phoenixwhisper.onrender.com/success/BzKtI9OfEpk/en).

We are excited to welcome you to the second episode of the Cohere AI Hackathon! In partnership with Cohere, we are giving lablab.ai community access to one of the most powerful AI language models on the market. Join us and innovate to build a better future for everyone!

Join us for a hackathon where we will be using OpenAI Whisper to create innovative solutions! Whisper is a neural net that has been trained to approach human level robustness and accuracy for English speech recognition. We will be using this tool to create applications that can transcribe in multiple languages, as well as translate from those languages into English. This will be a great opportunity for you to learn more about speech processing and to create some useful applications!

🗓️ This will be a 7-day virtual hackathon from 13-20 January 💻 Access AI21 Labs' state-of-the-art language models to build innovative applications 🏆 Prizes and awards of up to $9000 API credits + $3500 cash 💡 Meet and learn from AI21 Labs and Lablab experts 👥 Join the community and find your team ✔️ All levels are welcome 📖 AI tutorials and mentors to help you ⭐ Receive a certificate of completion and Wordtune premium for submission 🐱‍💻 Sign up now! It’s free!