declare-lab/speech-adapters

Codes and datasets for our ICASSP2023 paper, Evaluating parameter-efficient transfer learning approaches on SURE benchmark for speech understanding

41
/ 100
Emerging

This project helps machine learning engineers efficiently adapt large pre-trained speech models for specific speech understanding tasks like emotion recognition or intent classification. It takes a pre-trained speech model and a specific speech dataset as input, then outputs a specialized model capable of performing well on that task without needing to retrain the entire large model. This is for machine learning engineers working on various speech AI applications.

No commits in the last 6 months.

Use this if you need to quickly and efficiently adapt large, pre-trained speech models to new, specific speech understanding tasks like speech emotion recognition or spoken language understanding, without the computational cost and risk of overfitting associated with full model fine-tuning.

Not ideal if you are building a speech model from scratch or if you do not have access to pre-trained large speech models.

speech-recognition natural-language-understanding audio-processing machine-learning-operations model-adaptation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

42

Forks

8

Language

Python

License

MIT

Last pushed

Mar 12, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/declare-lab/speech-adapters"

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