athena-team/athena
an open-source implementation of sequence-to-sequence based speech processing engine
Built on TensorFlow 2.0+, Athena supports multiple speech processing tasks (ASR, TTS, VAD, KWS) with hybrid attention/CTC architectures, WFST-based decoding, and distributed multi-GPU training via Horovod. It includes a Kaldi-free feature extraction library (Athena_transform) and C++ runtime for inference with local server deployment capabilities. The framework provides end-to-end and streaming model variants across diverse datasets (AISHELL-1, LibriSpeech, GigaSpeech) with reference recipes and pre-trained model zoo support.
970 stars. No commits in the last 6 months.
Stars
970
Forks
199
Language
C++
License
Apache-2.0
Category
Last pushed
Dec 02, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/athena-team/athena"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
githubharald/CTCWordBeamSearch
Connectionist Temporal Classification (CTC) decoder with dictionary and language model.
githubharald/CTCDecoder
Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon...
nl8590687/ASRT_SpeechRecognition
A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统
hirofumi0810/tensorflow_end2end_speech_recognition
End-to-End speech recognition implementation base on TensorFlow (CTC, Attention, and MTL training)
rakeshvar/rnn_ctc
Recurrent Neural Network and Long Short Term Memory (LSTM) with Connectionist Temporal...