ddlBoJack/MT4SSL

[INTERSPEECH 2023 Best Paper Shortlist] Official implementation for MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets

33
/ 100
Emerging

This project helps machine learning engineers and researchers accelerate the training of speech recognition models. It takes raw audio data and various pre-training targets as input and outputs a fine-tuned model capable of transcribing speech efficiently. This is designed for those who develop or enhance speech AI systems.

No commits in the last 6 months.

Use this if you are developing new speech recognition models and want to achieve strong performance with fewer pre-training steps and faster convergence.

Not ideal if you are looking for an off-the-shelf speech recognition application rather than a framework for model development.

speech-recognition machine-learning-engineering audio-processing AI-model-development
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

45

Forks

4

Language

Python

License

MIT

Last pushed

Mar 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ddlBoJack/MT4SSL"

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