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")