ondrejklejch/learning_to_adapt

Coordinate-wise meta-learner for speaker adaptation of ASR models.

38
/ 100
Emerging

When building Automatic Speech Recognition (ASR) models, this helps improve how well they understand different individual speakers. It takes your existing ASR model and audio data from specific speakers to fine-tune the model, making it more accurate for those individual voices. Speech scientists and engineers working on ASR systems would use this to enhance personalization.

No commits in the last 6 months.

Use this if you need to significantly improve the accuracy of an ASR model for specific speakers after initial training.

Not ideal if you are looking for a general-purpose ASR model that doesn't require adaptation to individual speakers.

speech-recognition speaker-adaptation voice-AI acoustic-modeling ASR-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

20

Forks

7

Language

Python

License

Apache-2.0

Last pushed

Dec 30, 2019

Commits (30d)

0

Get this data via API

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

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