HawkAaron/E2E-ASR

PyTorch Implementations for End-to-End Automatic Speech Recognition

38
/ 100
Emerging

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.

speech-to-text voice-recognition natural-language-processing deep-learning-research audio-transcription
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 20 / 25

How are scores calculated?

Stars

127

Forks

25

Language

Python

License

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.