Conformer-2: A state-of-the-art speech recognition model

We're introducing Conformer-2, our latest AI model for automatic speech recognition. Conformer-2 is trained on 1.1M hours of English audio data, extending Conformer-1 to provide improvements on proper nouns, alphanumerics, and robustness to noise.

Conformer-2 builds on our original release of Conformer-1, improving both model performance and speed in our automated speech recognition model. Conformer-1 model achieved state-of-the-art performance (previous results), and demonstrated strong noise robustness making it well suited for the type of real world audio conditions our customers …

ai model art audio automated automated speech recognition automatic speech recognition data english noise performance recognition release robustness speech speech recognition speed state