Home / Unlabelled / Mozilla’s Open Source Speech Recognition Model and Voice Dataset

Mozilla’s Open Source Speech Recognition Model and Voice Dataset

Mozilla has just announced the initial release of Mozilla's open source speech recognition model that has an accuracy approaching what humans can perceive when listening to the same recordings. They are also releasing the world's second-largest publicly available voice dataset, which was contributed to by nearly 20,000 people globally. This looks like it will be a very useful resource for researchers.

from The Universal Machine http://universal-machine.blogspot.com/
RSS Feed

Universal Machine post to email (CS blog)

IFTTT
Mozilla’s Open Source Speech Recognition Model and Voice Dataset Mozilla’s Open Source Speech Recognition Model and Voice Dataset Reviewed by Doctor Smile on December 10, 2017 Rating: 5
Subscribe to: Post Comments ( Atom )

Post Comments

No comments:

Instagram Is Divided Over MAC's Decision To Leave Facial Hair In Photos

Earlier this month, Urban Decay's decision to embrace "real skin" by sharing images of makeup artists showing off their pore...

Powered by Blogger.