Cristina Bunea

Whisper by OpenAI - A neural net for speech recognition

Whisper is an automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web.

Add a comment

Replies

Best
Cristina Bunea
Really curious to see how makers will use this to build other tools. Already seeing some interesting applications circulating on Twitter, like this subtitle generator for Youtube videos.
Mustapha Ajermou
OpenAi is good but unfortunately they are not accepting payment methods from Morocco.
Justin Mitchell
@mustapha_ajermou1 Bet there's a startup opportunity in a tool that lets you create a a US debit card from a foreign bank card or bank connection for times like this
Varun Razora
We might get this into our app soon but pricing, i don't see any pricing tab
Goran
@varunrazora it's free (https://github.com/openai/whisper) but it needs a strong GPU to run well. I'm sure it'll be available as a cloud offering in no time.
Varun Razora
@gorango Thanks for the info but we were trying to implement some open AI api with Elaxer before and it had some price tag which i don't remember. This really going to help many for sure. We are on AWS right now do you have idea about minimum GPU for smooth working.
Hardewale James
No matter how far you are... you are always in my thoughts
Om Wow
Mind. Blown. Both the English "speed talking" and the "accent" examples clearly show that AI is better at recognizing what is said than I am, and let's not even go to Korean and French. This is amazing!
Ash Rahman 🎮
Interesting implementation. Congrats on the launch!
Shushant Lakhyani
Congratulations on the launch!
Yash
Superb, will try it out!
Melinda Xiao-Devins
Tried out the model, great 👍 very good accuracy. Looking forward to the word level timestamp feature. It would enable our transcript based video editing at Visla.
Zast
Excellent and free. It's easy to use and the results are very good.