Excited to share our latest model - Universal-2 builds on Universal-1's foundation with major improvements in proper nouns, text formatting, and alphanumerics.
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:
Spent nearly a month in Europe, travelling through Lisbon, Azores, Switzerland, Munich (got to go to Oktoberfest! ๐ป) and Tromsรธ.
#goingplaces fr with @my_mokobara
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
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