---
language:
- lus
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- andrewbawitlung/mizonal-v3
metrics:
- wer
- cer
model-index:
- name: whisper-medium-mizonal3-E2-lus-v2026.06
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: MiZonal v3
      type: andrewbawitlung/mizonal-v3
      config: default
      split: test
    metrics:
    - name: Wer
      type: wer
      value: 21.7728
    - name: Cer
      type: cer
      value: 7.3593
    - name: Real Time Factor
      type: rtf
      value: 0.0520
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# whisper-medium-mizonal3-E2-lus-v2026.06

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the **MiZonal v3** dataset. 
Note: ~1 hour of conversational speech was added to this dataset version.

It achieves the following results on the evaluation set:
- Wer: 21.7728
- Cer: 7.3593
- Real Time Factor: 0.0520

## 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](https://huggingface.co/andrewbawitlung/whisper-medium-mizonal3-E1-lus-v2026.06) |
| **E2 (Noise)** | [andrewbawitlung/whisper-medium-mizonal3-E2-lus-v2026.06](https://huggingface.co/andrewbawitlung/whisper-medium-mizonal3-E2-lus-v2026.06) |
| **E3 (Speed)** | [andrewbawitlung/whisper-medium-mizonal3-E3-lus-v2026.06](https://huggingface.co/andrewbawitlung/whisper-medium-mizonal3-E3-lus-v2026.06) |
| **E4 (SpecAug)** | [andrewbawitlung/whisper-medium-mizonal3-E4-lus-v2026.06](https://huggingface.co/andrewbawitlung/whisper-medium-mizonal3-E4-lus-v2026.06) |
| **E5 (Combined)** | [andrewbawitlung/whisper-medium-mizonal3-E5-lus-v2026.06](https://huggingface.co/andrewbawitlung/whisper-medium-mizonal3-E5-lus-v2026.06) |

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### 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 | 0.4553734061930783 | 0.6866 | 0.6109971404075623 | 0.34260971100515714 | 0.12720879276222788 | 0.0001494 | 7.834379196166992 |
| 500 | 0.9107468123861566 | 0.8029 | 0.8720874786376953 | 0.6379293568161915 | 0.3605103194797851 | 0.00029939999999999996 | 20.601097106933594 |
| 750 | 1.366120218579235 | 0.6327 | 0.7277008295059204 | 0.36489247834971295 | 0.1706071529544812 | 0.0002808067831449126 | 5.541914939880371 |
| 1000 | 1.8214936247723132 | 0.4858 | 0.6909858584403992 | 0.34484771820570204 | 0.14426067288662708 | 0.00026153648509763614 | 3.856584310531616 |
| 1250 | 2.276867030965392 | 0.3171 | 0.6292513608932495 | 0.3085530796925173 | 0.12282654792196777 | 0.00024226618705035967 | 3.361140251159668 |
| 1500 | 2.73224043715847 | 0.264 | 0.6323882937431335 | 0.3075800330835847 | 0.11938083121289228 | 0.00022299588900308323 | 3.037963628768921 |
| 1750 | 3.1876138433515484 | 0.1781 | 0.6203708052635193 | 0.3519509584509098 | 0.1572307039864292 | 0.00020372559095580676 | 2.4910476207733154 |
| 2000 | 3.6429872495446265 | 0.1584 | 0.6050002574920654 | 0.2888975381920794 | 0.11347893695221939 | 0.0001844552929085303 | 2.562002658843994 |
| 2250 | 4.098360655737705 | 0.0972 | 0.6101962924003601 | 0.2805293373552593 | 0.11922179813401187 | 0.00016518499486125384 | 1.7251062393188477 |
| 2500 | 4.553734061930784 | 0.0894 | 0.5966487526893616 | 0.25338133696604065 | 0.09407690132880972 | 0.0001459146968139774 | 1.6773935556411743 |
| 2750 | 5.009107468123862 | 0.0659 | 0.6184111833572388 | 0.24958645519120365 | 0.09423593440769014 | 0.00012664439876670092 | 0.9618287086486816 |
| 3000 | 5.46448087431694 | 0.0524 | 0.6331346035003662 | 0.2560085628101586 | 0.10946776929601357 | 0.00010737410071942445 | 1.4324769973754883 |
| 3250 | 5.919854280510018 | 0.0345 | 0.6023192405700684 | 0.23255813953488372 | 0.08416383941193102 | 8.810380267214798e-05 | 0.7218911647796631 |
| 3500 | 6.375227686703097 | 0.0192 | 0.5783641934394836 | 0.24832149459959132 | 0.10796579021769862 | 6.883350462487152e-05 | 0.2467842400074005 |
| 3750 | 6.830601092896175 | 0.0097 | 0.6010708808898926 | 0.2191300963316143 | 0.08168999151823579 | 4.956320657759506e-05 | 0.12510214745998383 |
| 4000 | 7.285974499089253 | 0.0038 | 0.596376895904541 | 0.2028802179624404 | 0.07089341249646593 | 3.0292908530318598e-05 | 0.12478488683700562 |
| 4250 | 7.741347905282332 | 0.002 | 0.6114839911460876 | 0.19976646881385618 | 0.06813683912920554 | 1.1022610483042137e-05 | 0.009769609197974205 |