#158 · Primary category： Speech & Audio
athena
an open-source implementation of sequence-to-sequence based speech processing engine
Project last updated：12/02/22
GitHub Stars
966
Forks
197
Contributors
37
License
Apache-2.0
Why we included this project
Athena is a solid pick when your speech work runs inside TensorFlow and you want more than a single demo model. It covers the full pipeline: hybrid attention/CTC recognition with streaming support, text-to-speech through FastSpeech and FastSpeech2 (Tacotron2 and HiFi-GAN vocoding also show up in the repo), voice activity detection, and keyword spotting. Recipes with published result tables on AISHELL-1, LibriSpeech, GigaSpeech, and LJSpeech make it easy to reproduce solid baselines before adapting them to your own data. On the production side, the C++ runtime provides WFST decoding and a TensorFlow C++ local server for serving trained models, while the Kaldi-free Python feature extractor spares teams who never picked up the Kaldi toolchain.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
whisper.cpp
Port of OpenAI's Whisper model in C/C++
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
VibeVoice
Open-Source Frontier Voice AI
voicebox
The open-source AI voice studio. Clone, dictate, create.
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production