biyoml/PyTorch-End-to-End-ASR-on-TIMIT

Attention-based end-to-end ASR on TIMIT in PyTorch

30
/ 100
Emerging

This project helps researchers and students working on speech recognition by providing a robust system for converting spoken audio into phoneme sequences. You feed it audio recordings from the TIMIT dataset, and it outputs the phonetic transcription of the speech. This is ideal for those studying or experimenting with end-to-end automatic speech recognition (ASR) models.

No commits in the last 6 months.

Use this if you need a working, attention-based model to transcribe speech phonetically from the TIMIT dataset and want to reproduce or build upon established ASR research.

Not ideal if you need to transcribe speech into text (words, not phonemes) or work with a different speech dataset outside of TIMIT.

speech-recognition phonetics acoustic-modeling natural-language-processing computational-linguistics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

18

Forks

6

Language

Python

License

Last pushed

Nov 09, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/biyoml/PyTorch-End-to-End-ASR-on-TIMIT"

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