athena
Athena is an open-source engine for end-to-end speech processing, suitable for both industrial and research applications. Built on Tensorflow, it includes models for tasks such as ASR, TTS, VAD, and KWS. Athena supports hybrid attention/CTC models, multi-GPU training with Horovod, and WFST-based decoding. Recent enhancements allow Tensorflow C++ deployment and introduce models like AV-Transformer and Conformer-CTC. The platform aims to make advanced speech processing accessible to all, backed by thorough documentation and community resources.
