---
language:
  - ja
license: apache-2.0
base_model: Qwen/Qwen3-ASR-1.7B
tags:
  - automatic-speech-recognition
  - japanese
  - qwen3_asr
pipeline_tag: automatic-speech-recognition
---

# lilfugu-transformers

Transformers-compatible (fp16) version of [lilfugu](https://huggingface.co/holotherapper/lilfugu) for CUDA / Linux. See the main model card for details.

## Usage

```python
from qwen_asr import Qwen3ASRModel

model = Qwen3ASRModel.from_pretrained("holotherapper/lilfugu-transformers")
result = model.transcribe("audio.wav")
```