Downloads · 30 days
0
Qwen3-ASR-LoRa-ChineseAviation-Tiny
ha0yuan/Qwen3-ASR-LoRa-ChineseAviation-Tiny
Qwen3-ASR-LoRa-ChineseAviation-Tiny is a automatic speech recognition model from ha0yuan. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
[](https://github.com/ysys12138/Qwen3-ASR-Lora-finetune) [](https://huggingface.co/ysys12138/Qwen3-ASR-Lora-Chinese)
Access
Public
Updated Mar 11, 2026
Repo size
338 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt218 MB · 64%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Mar 11, 2026
- Updated
- Mar 11, 2026
- SHA
- c3788d68
Base models
Datasets
Model card
From the Hugging Face model README
Qwen3-ASR LoRA Chinese Fine-tuned Model
Model Description
This model is a LoRA fine-tuned version of Qwen/Qwen3-ASR-1.7B for Chinese speech recognition. The fine-tuning was performed using the PEFT library with LoRA method.
- Base model: Qwen/Qwen3-ASR-1.7B
- Fine-tuning method: LoRA
- Language: Chinese
- Task: Automatic Speech Recognition
Fine-tuning Details
- LoRA rank: 16
- LoRA alpha: 32
- LoRA dropout: 0.05
- Target modules: all-linear
- Batch size: 4
- Learning rate: 2e-4
- Epochs: 20
- Warmup ratio: 0.05
Usage
Installation
pip install transformers peft torch audio
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Languages
- zh, en
- Created
- Mar 11, 2026
- Updated
- Mar 11, 2026