Deepgram Expands to 23 Language and Dialect Speech Models

Today automatic speech recognition company Deepgram launched 23 language and dialect models.

The current lineup of supported languages and dialects includes the following: Dutch, U.S., U.K., Australian, and Indian English, European and Canadian French, German, Hindi, Indonesian, Italian, Japanese, Korean, simplified and traditional Mandarin Chinese, European and Brazilian Portuguese, Russian, European and Latin American Spanish, Swedish, Turkish, and Ukrainian.

"At Deepgram, we understand that speech is complicated. People have unique accents or dialects that can be difficult for an all-in-one or global solution to transcribe accurately. If your business has international locations or customers, you need a speech recognition solution that can deliver the same level of accuracy, regardless of language or dialect," Keith Lam, head of product marketing at Deepgram, wrote in a blog post. "This announcement marks Deepgram's commitment to expanding to new regions and improving accuracy for as many users as possible. Adding this new suite of languages is a significant step toward delivering a global language experience that is on par with the success we've seen from our U.S. English model."

According to Lam, Deepgram developed the new language models using transfer learning backed by its End-to-End Deep Learning architecture and training with real-world audio datasets.

The company, he added, is planning to release even more languages in the coming year.;