The AssemblyAI blog post "Conformer-2: A state-of-the-art speech recognition model" introduces Conformer-2, AssemblyAI's latest AI model for automatic speech recognition (ASR). Conformer-2 is trained on 1.1M hours of English audio data, making it the largest and most comprehensive ASR model ever trained. Conformer-2 achieves state-of-the-art accuracy on a variety of academic and real-world datasets, including…