Downloads · 30 days
0
lilfugu-lora
holotherapper/lilfugu-lora
lilfugu-lora is a automatic speech recognition model from holotherapper. Use it when you need speech turned into text. It is set up for mlx. The card lists the license as apache-2.0.
LoRA adapter for lilfugu. Apply to Qwen3-ASR-1.7B-bf16 with adjustable scale.
Access
Public
Updated Apr 12, 2026
Repo size
51.4 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors51.4 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- mlx
- License
- apache-2.0
- Access
- Public
- Created
- Apr 12, 2026
- Updated
- Apr 12, 2026
- SHA
- bf9f155c
Base models
Model card
From the Hugging Face model README
lilfugu-lora
LoRA adapter for lilfugu. Apply to Qwen3-ASR-1.7B-bf16 with adjustable scale.
Usage
from mlx_tune.stt import FastSTTModel
from mlx_lm.tuner.lora import LoRALinear
model, _ = FastSTTModel.from_pretrained("mlx-community/Qwen3-ASR-1.7B-bf16")
model.load_adapter("holotherapper/lilfugu-lora")
# Adjust scale (0.0-1.0). Higher = stronger term conversion.
for _, module in model.model.named_modules():
if isinstance(module, LoRALinear):
module.scale = 1.0
text = model.transcribe("audio.wav", language="ja")
- Task
- Automatic Speech Recognition
- Library
- mlx
- License
- apache-2.0
- Languages
- ja
- Created
- Apr 12, 2026
- Updated
- Apr 12, 2026