declare-lab/speech-adapters
Codes and datasets for our ICASSP2023 paper, Evaluating parameter-efficient transfer learning approaches on SURE benchmark for speech understanding
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.
Stars
42
Forks
8
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
srvk/eesen
The official repository of the Eesen project