jiwidi/las-pytorch

Listen, Attend and spell model for E2E ASR. Implementation in Pytorch

26
/ 100
Experimental

This project offers a foundational implementation for converting spoken language into written text using deep learning. It takes raw audio files as input and outputs a sequence of predicted letters, aiming to transcribe speech accurately. Researchers and engineers working on speech-to-text systems or exploring deep learning architectures for audio processing would find this useful for experimentation and model development.

No commits in the last 6 months.

Use this if you are a researcher or engineer looking for a Pytorch implementation of the Listen, Attend and Spell model for Automatic Speech Recognition (ASR) to experiment with or build upon.

Not ideal if you need a production-ready, highly accurate speech-to-text solution out-of-the-box for immediate use.

Speech Recognition Natural Language Processing Deep Learning Audio Processing Machine Learning Research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

42

Forks

4

Language

Python

License

Last pushed

Jun 22, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jiwidi/las-pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.