Yash Khare

Deep Learning Researcher @AssemblyAI 🎶 | Exploring the world 🗺️

[Yash Khare @_p0lar_bear]

@abhijitramesh2k Any walk is a micro walk if you’re @akhlkg

[AssemblyAI @AssemblyAI]

Check out our recent paper on our innovative all-neural text formatting model, which powers Universal-2! 👇

https://t.co/mqvPN1zEgI

[Yash Khare @_p0lar_bear]

Checkout how we did this here: https://t.co/NJYMFqTxaQ

[Yash Khare @_p0lar_bear]

Excited to share our latest model - Universal-2 builds on Universal-1's foundation with major improvements in proper nouns, text formatting, and alphanumerics.

[AssemblyAI @AssemblyAI]

Announcing Universal-2, our most advanced speech-to-text model to date.

Building on Universal-1's industry-leading performance, we've pushed Speech AI even further. Here's what's new:

[Yash Khare @_p0lar_bear]

@anukaal @iamsh4shank We purchased shoes👞

[Yash Khare @_p0lar_bear]

Did I ever tell you about the time I went backpacking through Western Europe?

[Yash Khare @_p0lar_bear]

@chromicle_3 @OpenAI I’ll talk to chatgpt about your personal life so it knows everything 🧠

[Yash Khare @_p0lar_bear]

Spent nearly a month in Europe, travelling through Lisbon, Azores, Switzerland, Munich (got to go to Oktoberfest! 🍻) and Tromsø.

#goingplaces fr with @my_mokobara

[Yash Khare @_p0lar_bear]

On a related note: The DB others want vs the DB I want 🚆

[Shashank Priyadarshi @iamsh4shank]

@_p0lar_bear Nature: creates breathtaking view…
Humans be like: Nice, but can we run it on the cloud?

[Yash Khare @_p0lar_bear]

@andrea_vanzo 📍São Miguel, Azores 🇵🇹

[Yash Khare @_p0lar_bear]

humans saw this and decided to invent GCP

[Yash Khare @_p0lar_bear]

@chromicle_3 I’ve got a nicer one in Banglore 👀

[Yash Khare @_p0lar_bear]

@vchrombie @roronoazoro_189 Ping

[Yash Khare @_p0lar_bear]

@qedk_ @kundraSarthak So hard to believe this.
Rest in peace Sarthak 🕊️

[Yash Khare @_p0lar_bear]

@vchrombie @nyutandon Congratulations! 🥳🥳

[Yash Khare @_p0lar_bear]

@LearnedVector Congrats Michael!! LFG 🚀

[Yash Khare @_p0lar_bear]

Thrilled to share the latest model from @AssemblyAI, Universal-1 - a state of the art multilingual speech-to-text model, trained on over 12 million hours of audio: https://t.co/5F1mjCgiEe

We have also released a paper on our Conformer-1 architecture: https://t.co/jnbn8Nnfmg

[AssemblyAI @AssemblyAI]

Introducing Universal-1, our most powerful speech recognition model to date.

Trained on over 12.5 million hours of multilingual audio data, Universal-1 achieves best-in-class speech-to-text accuracy across English, Spanish, French, and German.

https://t.co/xgrE6EhmJu

[Yash Khare @_p0lar_bear]

@abhijitramesh2k Well it is a big cross icon 😂

[Yash Khare @_p0lar_bear]

@cheesetaco19 @iamsh4shank Which one would dat be? 👀