HawkAaron/E2E-ASR
PyTorch Implementations for End-to-End Automatic Speech Recognition
This project helps researchers and engineers develop and evaluate automatic speech recognition (ASR) systems. You can input speech audio features (like Kaldi fbank features) and train models that output transcribed text. It's designed for someone working on building or improving speech-to-text technology, such as an AI researcher or a machine learning engineer specializing in audio.
127 stars. No commits in the last 6 months.
Use this if you need to experiment with and train end-to-end automatic speech recognition models, specifically using the CTC or RNN-T architectures described in the Graves 2012 and 2013 papers.
Not ideal if you are looking for an out-of-the-box speech-to-text application for end-users, or if you prefer using pre-trained models without deep customization.
Stars
127
Forks
25
Language
Python
License
—
Category
Last pushed
Jun 10, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/HawkAaron/E2E-ASR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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
srvk/eesen
The official repository of the Eesen project