Speech Recognition: Parakeet

Model Overview

Parakeet-RNNT-XXL-1.1B (around 1.1B parameters) is trained on ASRSet with over 150000 hours of English (en-US) speech. The model transcribes speech in lower case English alphabet along with spaces and apostrophes.

Model Architecture

Parakeet-RNNT-XXL-1.1B (also known as FastConformer-RNNT) model [1] is a variant of Conformer model [2] for Automatic Speech Recognition which uses FastConformer and RNNT/Transducer loss/decoding. For more information, refer to the Conformer-Transducer Model and Fast-Conformer Model documentation.

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 dialog, all of which contribute to the model’s accuracy. OpenAI's opensource Whisper-v3 model was used to generate pseudo labels for a part of dataset. 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

The Riva Quick Start Guide is recommended as the starting point for trying out Riva models. For more information on using this model with Riva Speech Services, see the Riva User Guide.

Input

Audio sample that is to be transcribed

Output

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

References

[1] Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition
[2] Conformer: Convolution-augmented Transformer for Speech Recognition

Suggested Reading

Refer to the Riva documentation for more information.

License

By downloading and using the models and resources packaged with Riva Conversational AI, you accept the terms of the Riva license.

Ethical AI

NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.