---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-tiny-minds14
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: PolyAI/minds14
      type: PolyAI/minds14
    metrics:
    - name: Wer
      type: wer
      value: 0.3482880755608028
---

<!-- 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-tiny-minds14

This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4687
- Wer: 0.3483
- Wer Ortho: 0.3609

## Model description

More information needed

## 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    | Wer Ortho |
|:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|
| 3.2197        | 1.0   | 29   | 2.3350          | 0.3973 | 0.5231    |
| 1.8109        | 2.0   | 58   | 0.6575          | 0.3796 | 0.4170    |
| 0.6252        | 3.0   | 87   | 0.4859          | 0.3583 | 0.3720    |
| 0.3612        | 4.0   | 116  | 0.4680          | 0.3613 | 0.3726    |
| 0.2543        | 5.0   | 145  | 0.4687          | 0.3483 | 0.3609    |


### Framework versions

- Transformers 4.57.0
- Pytorch 2.8.0+cu126
- Datasets 4.1.1
- Tokenizers 0.22.1