Chirp
Chirp is a version of a Universal Speech Model that has over 2B parameters and can transcribe in over 100 languages in a single model.Chirp is a version of Google's Universal Speech Model (USM). The Universal Speech Model was first proposed in "Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages" by Zhang et. al. Chirp is different from previous speech models in that it leverages a universal encoder which is trained on data in many different languages. The model is then fine tuned to offer transcription for specific languages.
Chirp is a version of a Universal Speech Model that has over 2B parameters and can transcribe in over 100 languages in a single model. Chirp achieves state-of-the-art Word Error Rate (WER) on a variety of public test sets and languages.
Chirp is available through the Cloud Speech-to-Text API. The API lets you do inference for transcription against the Chirp model. View the Universal Speech Model quickstart to get started with Chirp on the Speech-to-Text API.
You can also try out recognition by using Chirp on the Speech-to-Text console page.
Resource ID | Release date | Release stage | Description |
---|---|---|---|
chirp-rnnt2 | 2023-07-18 | GA | |
chirp-rnnt1 | 2024-04-01 | General Availability | Initial release |
La console Google Cloud n'a pas pu charger les sources JavaScript depuis www.gstatic.com.
Voici les raisons possibles :