matthijsvk/TIMITspeech

Speech recognition on the TIMIT (or any other) dataset

33
/ 100
Emerging

This project helps researchers and engineers analyze speech audio by classifying individual phonemes within spoken words. You provide audio files and their corresponding phoneme labels, and it trains a neural network to identify phonemes at specific points in the audio. It's designed for speech recognition researchers and those developing spoken language processing systems.

No commits in the last 6 months.

Use this if you need to preprocess audio datasets and train a neural network for frame-wise phoneme classification to analyze speech data.

Not ideal if you're looking for a complete, out-of-the-box speech-to-text transcription system or if you specifically require a CTC-based model.

speech-recognition phonetics audio-analysis computational-linguistics spoken-language-processing
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

44

Forks

11

Language

Python

License

Last pushed

Nov 02, 2017

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/matthijsvk/TIMITspeech"

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