ga642381/SpeechPrompt

**Interspeech 2022** 《SpeechPrompt: An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks》Speech processing with prompting paradigm

28
/ 100
Experimental

This project helps speech processing engineers and researchers more efficiently adapt large pre-trained spoken language models for specific tasks like keyword spotting or intent classification. It takes raw speech audio and task labels as input, and outputs a fine-tuned model that can perform classification or even generate speech. This is intended for those who work with speech data and want to leverage state-of-the-art models without extensive computational resources.

101 stars. No commits in the last 6 months.

Use this if you need to adapt a large generative spoken language model for new speech classification or generation tasks with significantly fewer trainable parameters and computational cost than traditional fine-tuning.

Not ideal if you are looking for an off-the-shelf solution that doesn't require familiarity with model training pipelines or if your primary goal is to train a model from scratch without leveraging pre-trained foundations.

speech-recognition audio-classification spoken-language-processing natural-language-understanding speech-synthesis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

101

Forks

9

Language

Python

License

Last pushed

Apr 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/ga642381/SpeechPrompt"

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