Subscribe
Sign in
Universal-1 — Multilingual speech AI model trained on 12.5M hours of data
Try AssemblyAI's most capable and highly trained speech recognition model trained on 12.5M hours of multilingual audio data. Universal-1 achieves best-in-class speech-to-text accuracy, reduces word error rate and hallucinations, and improves timestamps.
22
Replies
@meredith_rauch Awesome! How close is it to human level interpretation? Are we 75% there or? What's the benchmark? Or is there a benchmark?
@sentry_co Great question! Universal-1 in English came in at 92.7% accuracy across multiple datasets. We display all benchmarks here: https://www.assemblyai.com/bench...
If you'd like to see a more in depth analysis of Universal-1, I highly recommend you check out our research which includes Word Error Rate by language, timestamp accuracy, hallucinations, and more. > https://www.assemblyai.com/resea...
Hope this helps! :)
@meredith_rauch I think there could be a clearer benchmark 92.7% against what?. I.e: Humans can interpret gibberish, or very chopped up or noisy audio. By filling in the blanks, or using context.
Congratulations on the launch! How did you manage to ensure high accuracy for languages with fewer training data?
Great launch! How does Universal-1 handle multilingual support and accuracy across different languages?
Congratulations on the launch! It's fantastic to see your product achieving a higher accuracy in voice recognition than many big companies. It's truly impressive and admirable. In the future, if my product development involves voice recognition, I will definitely consider using your API!
@alain_gold1 Our Best tier supports Korean and includes speaker labels, custom spelling, automatic punctuation, etc. We encourage you to try our API for free - more on supported languages and account creation here: https://www.assemblyai.com/docs/...
The Universal-1 Speech-to-Text model sounds incredibly promising! Since I use tools like this often for my work, I was wondering can you share some examples of the unique challenges you faced in achieving high accuracy across different tones and speaking styles?
Excited to test this. Does the playground currently allow us to access this model? Or will it soon?
I'm assuming part of what makes this work well is the same process you've been using, with word prediction based on context, as opposed to straight word for word phonetic reproduction of what it "hears"?
@1lastshot Yes, the playground is currently utilizing Universal-1! You will be able to select tiers, and Universal-1 currently falls under [Best]. More on our tiers and research here: https://www.assemblyai.com/blog/...
@meredith_rauch appreciate the reply and confirmation. I assume this probably works well for cleaner audio, but I'm finding newer transcription iterations, including universal 1after testing, are actually regressing for muddier audio. Their tendency to rewrite and predict what was supposedly said, as opposed to just trying its best to phonetically reproduce word for word, is resulting in compelling looking but pretty far off results. Is there a way to adjust for this on our end?
Congratulations on the launch 🎊
I think this can be used for converting podcasts into blogs.🤔
AssemblyAI