GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
vadimbelsky
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
vadimbelsky
Model Tree
Qwen/Qwen3-ASR-1.7B
Input Modalities
Output Modalities
Supported Functionality
| Metric | Zero-shot (base) | Fine-tuned | Improvement |
|---|---|---|---|
| WER | 14.41% | 11.49% | -20% |
| CER | 6.57% | 5.78% | -12% |
Evaluated on 849 KSA Arabic validation samples.
python
from qwen_asr import Qwen3ASRModelmodel = Qwen3ASRModel.from_pretrained("vadimbelsky/qwen3-asr-arabic-ksa")result = model.transcribe("audio.wav", language="Arabic")print(result)
Or with transformers directly:
python
from transformers import AutoModelForCausalLM, AutoProcessormodel = AutoModelForCausalLM.from_pretrained("vadimbelsky/qwen3-asr-arabic-ksa")processor = AutoProcessor.from_pretrained("vadimbelsky/qwen3-asr-arabic-ksa")
Apache 2.0 (same as base model)