asrt speech recognition

We have hosted the application asrt speech recognition in order to run this application in our online workstations with Wine or directly.

Quick description about asrt speech recognition:

ASRT is an end-to-end deep-learning Chinese ASR system built with TensorFlow/Keras, using convolution + CTC and a Max-Entropy HMM language model. It provides a REST/gRPC server backend and client SDKs in multiple languages (Python, Java, Go, Windows). Notably lightweight, it performs well without needing GPU acceleration and runs across platforms, targeting developers and researchers building Chinese voice interfaces.

Features:

• CTC-based ASR using TensorFlow/Keras
• Integrated MaxEnt�HMM Chinese language model
• RESTful and gRPC server endpoints
• Cross-platform Python client SDK
• Works on CPU or GPU with similar performance
• Targeted for research and deployment

Programming Language: Python.
Categories: