vectominist/End-to-end-ASR-Pytorch-DLHLP

Joint CTC-Attention End-to-end Speech Recognition - PyTorch Implementation (Deep Learning for Human Language Processing Special Project)

37
/ 100
Emerging

This project helps speech technologists and researchers build and experiment with automatic speech recognition (ASR) systems. It takes audio recordings as input and outputs the transcribed text, enabling the creation of custom voice assistants or transcription services. It is ideal for those involved in developing or improving speech-to-text technology, especially for specific domains or nuanced audio like whispered speech.

No commits in the last 6 months.

Use this if you are a speech recognition researcher or engineer looking to train and test advanced end-to-end ASR models, especially with options for layer-wise transfer learning or whispered speech processing.

Not ideal if you are looking for an out-of-the-box solution for general speech transcription without deep technical customization, or if you do not have access to GPU hardware for training.

speech-to-text voice-technology natural-language-processing audio-transcription acoustic-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

17

Forks

5

Language

Python

License

MIT

Last pushed

Nov 22, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/vectominist/End-to-end-ASR-Pytorch-DLHLP"

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