Kyubyong/specAugment

Tensor2tensor experiment with SpecAugment

38
/ 100
Emerging

This project helps speech recognition engineers improve their automatic speech recognition (ASR) models by augmenting speech data. It takes raw speech audio and applies techniques like frequency and time masking to the spectrograms. The output is a more robust ASR model, capable of better performance in real-world scenarios.

No commits in the last 6 months.

Use this if you are developing automatic speech recognition systems and want to improve your model's accuracy and generalization by making your training data more diverse.

Not ideal if you are not working with speech data or if your primary goal is not improving speech recognition model performance.

speech-recognition audio-processing machine-learning-engineering model-training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

46

Forks

7

Language

Python

License

Apache-2.0

Last pushed

May 13, 2019

Commits (30d)

0

Get this data via API

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

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