Downloads · 30 days
30
27% of all-time downloads
azni-uz/qwen3-asr-uzbek
qwen3-asr-uzbek is a automatic speech recognition model from azni-uz. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
Fine-tuned Qwen/Qwen3-ASR-1.7B for Uzbek speech-to-text.
Downloads · 30 days
30
27% of all-time downloads
All-time downloads
110
Public
Parameters
2B
4.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors4.1 GB · 100%
From the Hugging Face model README
Fine-tuned Qwen/Qwen3-ASR-1.7B for Uzbek speech-to-text.
import torch
from qwen_asr import Qwen3ASRModel
model = Qwen3ASRModel.from_pretrained(
"Gearnode/qwen3-asr-uzbek",
device_map="cuda:0",
dtype=torch.bfloat16,
attn_implementation="flash_attention_2",
max_new_tokens=448,
forced_aligner="Qwen/Qwen3-ForcedAligner-0.6B",
forced_aligner_kwargs=dict(dtype=torch.bfloat16, device_map="cuda:0"),
)
results = model.transcribe(
audio=[(audio_array, 16000)],
language=["Uzbek"],
return_time_stamps=True,
)
print(results[0].text)
| Model | Uzbek Quality | Notes |
|---|---|---|
| This model | Best | Some repetition handled by post-processing |
| Meta MMS (mms-1b-all) | Passable | Use lang code uzb-script_latin |
| Whisper large-v3 | Poor | Hallucination loops on Uzbek |
| Base Qwen3-ASR | Poor | Mixed languages |
Apache 2.0 (same as base model)