ESPnet

ESPnet is an open-source end-to-end speech processing toolkit designed for tasks such as speech recognition, text-to-speech, speech translation, speech enhancement, speaker diarization, and spoken language understanding. Utilizing PyTorch as its deep learning engine, ESPnet also incorporates Kaldi style data processing and feature extraction, providing users with a comprehensive setup for conducting various speech processing experiments. It is suitable for researchers, developers, and practitioners in the field of speech technology.