orbxball/timit-preprocessor

Extract mfcc vectors and phones from TIMIT dataset

22
/ 100
Experimental

This tool helps researchers and engineers working with speech recognition systems to prepare the TIMIT dataset. It takes raw TIMIT audio files and associated text, then processes them to produce MFCC (Mel-frequency cepstral coefficients) vectors and phonetic labels. This output is ready for use in developing and evaluating automatic speech recognition (ASR) models.

No commits in the last 6 months.

Use this if you are an ASR researcher or developer who needs to extract standard acoustic features and phone labels from the TIMIT corpus for model training and evaluation.

Not ideal if you are looking for a general-purpose audio processing tool or if you are not working specifically with the TIMIT dataset.

speech-recognition acoustic-phonetics ASR-development speech-data-preparation language-technology
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

16

Forks

Language

Shell

License

BSD-3-Clause

Last pushed

Mar 23, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/orbxball/timit-preprocessor"

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