Downloads · 30 days
21
16% of all-time downloads
andrewbawitlung/qwen3-asr-1.7b-mizonal3-E4-lus-v2026.06
qwen3-asr-1.7b-mizonal3-E4-lus-v2026.06 is a automatic speech recognition model from andrewbawitlung. Use it when you need speech turned into text. The card lists the license as apache-2.0.
Downloads · 30 days
21
16% of all-time downloads
All-time downloads
129
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

Disclaimer / Notice: Details for these are in Peer Review and publications of the paper will be made available soon for more details.
This model is a fine-tuned version of Qwen/Qwen3-ASR-1.7B on the MiZonal v3.0 dataset.
It achieves the following results on the evaluation set:
import torch
from qwen_asr import Qwen3ASRModel
# Load the model
model = Qwen3ASRModel.from_pretrained(
"andrewbawitlung/qwen3-asr-1.7b-mizonal3-E4-lus-v2026.06",
dtype=torch.bfloat16,
device_map="cuda:0" # Adjust device as needed
)
# Transcribe audio
results = model.transcribe("your_audio.wav")
print(results)
This repository is part of a series of experiments. The different configurations are:
| Experiment | Hugging Face Repository |
|---|---|
| E1 (Baseline) | andrewbawitlung/qwen3-asr-1.7b-mizonal3-E1-lus-v2026.06 |
| E2 (Noise) | andrewbawitlung/qwen3-asr-1.7b-mizonal3-E2-lus-v2026.06 |
| E3 (Speed) | andrewbawitlung/qwen3-asr-1.7b-mizonal3-E3-lus-v2026.06 |
| E4 (SpecAug) | andrewbawitlung/qwen3-asr-1.7b-mizonal3-E4-lus-v2026.06 |
| E5 (Combined) | andrewbawitlung/qwen3-asr-1.7b-mizonal3-E5-lus-v2026.06 |
The following hyperparameters were used during training:
| step | epoch | train_loss | eval_loss | eval_wer | eval_cer | learning_rate | grad_norm |
|---|---|---|---|---|---|---|---|
| 200 | 2.9018 | 0.4309 | 0.2885 | 24.5792 | 5.4760 | 1.31e-05 | 7.1875 |
| 400 | 5.8000 | 0.2051 | 0.2930 | 22.6331 | 5.2640 | 5.67e-06 | 6.0938 |