viig99/esolafast

Fast C++ implementation of ESOLA using KFRLib, can be used for online time-stretch augmentation during SpeechToText training.

31
/ 100
Emerging

This tool helps improve automatic speech recognition (ASR) systems by efficiently modifying audio data. It takes raw audio files as input and outputs time-stretched versions, making your ASR models more robust to variations in speech speed. It's designed for machine learning engineers and researchers who are training Speech-to-Text models.

No commits in the last 6 months.

Use this if you are an ML engineer training a Speech-to-Text model and need to quickly augment your audio datasets with time-stretched speech without sacrificing audio quality.

Not ideal if you are looking for a general-purpose audio editor or a tool for music production, as its primary focus is on speech augmentation for machine learning.

Speech-to-Text Audio Augmentation Machine Learning Training ASR Development Voice AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

16

Forks

2

Language

C++

License

MIT

Last pushed

Jul 25, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/viig99/esolafast"

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