This model is a fine-tuned version of openai/whisper-medium on the MiZonal v3.0 dataset. Note: ~1 hour of conversational speech was added to this dataset version.

It achieves the following results on the evaluation set:

Wer: 19.9372
Cer: 5.8077
Real Time Factor: 0.0525

Quick Inference

python

import torch
import librosa
from transformers import WhisperProcessor, WhisperForConditionalGeneration

device = "cuda" if torch.cuda.is_available() else "cpu"

processor = WhisperProcessor.from_pretrained("andrewbawitlung/whisper-medium-mizonal3-E4-lus-v2026.06")
model = WhisperForConditionalGeneration.from_pretrained("andrewbawitlung/whisper-medium-mizonal3-E4-lus-v2026.06").to(device)

audio, sr = librosa.load("your_audio.wav", sr=16000)
input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features.to(device)

with torch.no_grad():
    predicted_ids = model.generate(input_features, max_new_tokens=256)

transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]
print(transcription)

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/whisper-medium-mizonal3-E1-lus-v2026.06
E2 (Noise)	andrewbawitlung/whisper-medium-mizonal3-E2-lus-v2026.06
E3 (Speed)	andrewbawitlung/whisper-medium-mizonal3-E3-lus-v2026.06
E4 (SpecAug)	andrewbawitlung/whisper-medium-mizonal3-E4-lus-v2026.06
E5 (Combined)	andrewbawitlung/whisper-medium-mizonal3-E5-lus-v2026.06

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0003
train_batch_size: 8
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
250	0.91	0.6876	0.6007	75.55	48.97	1.49e-04	6.11
500	1.82	0.8456	0.8232	77.84	37.25	2.99e-04	9.15
750	2.73	0.6257	0.6778	46.98	23.99	2.56e-04	6.32
1000	3.64	0.4293	0.5844	29.30	10.78	2.12e-04	3.50
1250	4.55	0.2535	0.5866	26.82	9.56	1.68e-04	3.09
1500	5.46	0.1521	0.5415	23.69	10.97	1.24e-04	1.96
1750	6.36	0.0778	0.5008	22.02	7.08	7.96e-05	1.44
2000	7.27	0.0366	0.4628	19.28	6.15	3.55e-05	1.09