srvk/eesen
The official repository of the Eesen project
This project helps speech scientists and researchers build end-to-end Automatic Speech Recognition (ASR) systems. It takes raw speech audio as input and directly outputs transcribed text. This is designed for those who want to simplify the traditional ASR pipeline, bypassing complex components like Hidden Markov Models and Gaussian Mixture Models, using modern recurrent neural networks.
834 stars. No commits in the last 6 months.
Use this if you are developing ASR systems and want a streamlined, deep learning-based approach to convert speech audio into text.
Not ideal if you are looking for a pre-trained, off-the-shelf speech-to-text API or a tool for general audio processing.
Stars
834
Forks
339
Language
C++
License
Apache-2.0
Category
Last pushed
May 23, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/srvk/eesen"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
hirofumi0810/neural_sp
End-to-end ASR/LM implementation with PyTorch