Opensource

39 readers

1 users here now

This magazine is dedicated to discussions on open source software, hardware, and technology. Whether you are a developer, a tech enthusiast, or simply interested in the philosophy of open source, this is the place for you. Here you can share your knowledge, ask questions, and engage in discussions on topics such as open source programming languages, operating systems, hardware, and more. From the benefits and challenges of open source to the latest developments and trends, this category covers a wide range of topics related to open source.

founded 2 years ago

Whisper Large-v3 Release (github.com)

submitted 1 year ago by Even_Adder@lemmy.dbzer0.com to c/opensource@kbin.social

0 comments fedilink hide all child comments

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.

The large-v3 model shows improved performance over a wide variety of languages, and the plot below includes all languages where Whisper large-v3 performs lower than 60% error rate on Common Voice 15 and Fleurs, showing 10% to 20% reduction of errors compared to large-v2:

no comments (yet)

sorted by: hot top controversial new old

there doesn't seem to be anything here