Chirp: Automatic Speech Recognition for 100+ Languages | Research Bytes
Chirp is the next generation of our speech-to-text models. Representing the culmination of years of research, the first version of Chirp is now available for Speech-to-Text. The models can perform automatic speech recognition (ASR) on under-resourced languages, such as Amharic, Cebuano, and Assamese, in addition to widely spoken languages like English and Mandarin. We intend to improve and expand Chirp to more languages and domains.
Resources:
Get started with Chirp → https://goo.gle/3OTklFI
Watch more episodes of Research Bytes → https://goo.gle/ResearchBytes
Subscribe to the Google Research Channel → https://goo.gle/GoogleResearch
#GoogleResearch #GoogleAI