Modelpublic

KasuleTrevor/cdli-qwen3-asr-lg-typical-textpre-0p6b-finetune-or

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

0likes4downloads

Model Card

CDLI Qwen3-ASR Luganda Typical Speech Fine-tune from Text-Pre-Adapted Checkpoint

This repo contains checkpoint: checkpoint-12657.

Training Setup

—Base model: KasuleTrevor/cdli-qwen3-asr-lg-textpre-0p6b
—Datasets: KasuleTrevor/lg_100hrs + dmusingu/yogera-dataset (Luganda split)
—Task: Automatic Speech Recognition
—Language: Luganda

Notes

—This upload excludes training-state files to keep the repo clean.
—Checkpoint folder includes tokenizer and processor files needed for inference.
—Uploaded: 2026-05-28T03:03:58.327268+00:00