Speech Recognition: Conformer

Model Overview

Conformer-CTC (around 120M parameters) is trained on ASRSet with around 4500 hours of Hindi (hi-IN) speech. The model transcribes speech in Hindi alphabet along with spaces and apostrophes.

Model Architecture

Conformer-CTC [1] model is a non-autoregressive variant of Conformer model [1] for Automatic Speech Recognition which uses CTC loss/decoding instead of Transducer. For more information, refer to the Conformer-CTC 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. 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, refer to 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] Conformer: Convolution-augmented Transformer for Speech Recognition

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.

RIVA Conformer ASR Hindi