Speech Recognition: Citrinet

Model Overview

Citrinet-1024 model which has been trained on the ASR dataset with over 3500 hours of Korean(ko-KR) speech. It utilizes a Google SentencePiece [1] tokenizer with vocabulary size 1024, and transcribes text in lower case Korean alphabet along with spaces, apostrophes and a few other characters.

Model Architecture

Citrinet is a deep residual convolutional neural network architecture that is optimized for Automatic Speech Recognition tasks. There are many variants of the Citrinet family of models, which are further discussed in the paper [2].

Training

The model was trained on various proprietary and open-source datasets. These datasets include variety of accents, domain specific data for various domains, spontaneous speech and dialogue, all of which contribute to the model’s accuracy. This model delivers WER that is better than or comparable to popular alternate Speech to Text solutions for a range of domains and use cases.

How to Use this Model

To use this model , we can use Riva Skills Quick start guide , it is a starting point to try out Riva models . Information regarding Quick start guide can be found : here. To use Riva Speech ASR service using this model , document has all the necessary information.

Input

Audio sample that is to be transcribed

Output

This model provides transcribed speech as a string for a given audio sample.

References

[1] Google Sentencepiece Tokenizer

[2] Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition

License

By downloading and using the models and resources packaged with Riva Conversational AI, you would be accepting the terms of the Riva license