PigeonDan1/ps-slm
TASU: A New Style of Alignment of Speech LLM with only Text Training Data, zero-shot on ASR and Other SU tasks
This project helps speech AI researchers train Speech Large Language Models (Speech LLMs) to understand spoken language. It takes text-only datasets and audio files as input and outputs a trained Speech LLM capable of various speech understanding tasks. Scientists and researchers in natural language processing and speech technology would use this.
Use this if you are a speech AI researcher looking for a new, efficient way to align Speech LLMs for semantic understanding using primarily text-based training data.
Not ideal if you are an end-user looking for a ready-to-use application or a developer without expertise in large language model training and GPU/NPU cluster management.
Stars
22
Forks
2
Language
Python
License
—
Category
Last pushed
Jan 19, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/PigeonDan1/ps-slm"
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