import torch
from qwen_asr import Qwen3ASRModel

# Load the model
model = Qwen3ASRModel.from_pretrained(
    "andrewbawitlung/qwen3-asr-1.7b-mizonal3-E1-lus-v2026.06", 
    dtype=torch.bfloat16, 
    device_map="cuda:0"  # Adjust device as needed
)

# Transcribe audio
results = model.transcribe("your_audio.wav")
print(results)

Model description

Experiment Configurations

This repository is part of a series of experiments. The different configurations are:

E1 (Baseline): Standard training configuration.
E2 (Noise): Training with background noise augmentation.
E3 (Speed): Training with speed perturbation augmentation.
E4 (SpecAug): Training with SpecAugment (time and frequency masking).
E5 (Combined): Training with a combination of all augmentations.

All Models in this Family

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

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 8
seed: 42
optimizer: OptimizerNames.ADAMW_TORCH_FUSED
lr_scheduler_type: SchedulerType.LINEAR
num_epochs: 8

Training results

step	epoch	train_loss	eval_loss	eval_wer	eval_cer	learning_rate	grad_norm
200	2.9018	0.4432	0.2900	24.8613	5.5626	1.31e-05	7.5000
400	5.8000	0.2058	0.2927	22.8374	5.2552	5.67e-06	6.2500