orbxball/timit-preprocessor
Extract mfcc vectors and phones from TIMIT dataset
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.
Stars
16
Forks
—
Language
Shell
License
BSD-3-Clause
Category
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.
Featured in
Higher-rated alternatives
Uberi/speech_recognition
Speech recognition module for Python, supporting several engines and APIs, online and offline.
cmusphinx/pocketsphinx
A small speech recognizer
tensorflow/lingvo
Lingvo
modelscope/FunASR
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models,...
PyThaiNLP/pythaiasr
Python Thai Automatic Speech Recognition