Скачать или смотреть 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 regularly face. This research was inspired by the data and model parameter scaling laws presented in DeepMind’s Chinchilla paper [1] which is also a cornerstone of the current Large Language Model Generative AI space.

Try it out at our playground: https://www.assemblyai.com/playground...
▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT ▬▬▬▬▬▬▬▬▬▬▬▬

🖥️ Website: https://www.assemblyai.com/?utm_sourc...
🐦 Twitter:   / assemblyai  
🦾 Discord:   / discord  
▶️ Subscribe: https://www.youtube.com/c/AssemblyAI?...
🔥 We're hiring! Check our open roles: https://www.assemblyai.com/careers

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

#MachineLearning #DeepLearning