---
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
      config: en-US
      split: train
      args: en-US
    metrics:
    - name: Wer
      type: wer
      value: 0.4964580873671783
---

<!-- 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: 0.9507
- Wer Ortho: 0.4855
- Wer: 0.4965

## 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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer Ortho | Wer    |
|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|
| 0.7253        | 1.7857  | 50   | 0.5916          | 0.3751    | 0.3583 |
| 0.158         | 3.5714  | 100  | 0.6146          | 0.3399    | 0.3235 |
| 0.0244        | 5.3571  | 150  | 0.6676          | 0.3307    | 0.3264 |
| 0.0127        | 7.1429  | 200  | 0.6988          | 0.3251    | 0.3188 |
| 0.0065        | 8.9286  | 250  | 0.7239          | 0.3350    | 0.3329 |
| 0.0023        | 10.7143 | 300  | 0.7469          | 0.3344    | 0.3294 |
| 0.002         | 12.5    | 350  | 0.7677          | 0.3257    | 0.3217 |
| 0.0009        | 14.2857 | 400  | 0.7667          | 0.3208    | 0.3182 |
| 0.0009        | 16.0714 | 450  | 0.8388          | 0.3405    | 0.3388 |
| 0.0031        | 17.8571 | 500  | 0.7991          | 0.3313    | 0.3323 |
| 0.0003        | 19.6429 | 550  | 0.8032          | 0.3436    | 0.3406 |
| 0.0002        | 21.4286 | 600  | 0.8200          | 0.3418    | 0.3400 |
| 0.001         | 23.2143 | 650  | 0.8118          | 0.3436    | 0.3406 |
| 0.0005        | 25.0    | 700  | 0.8278          | 0.3344    | 0.3323 |
| 0.0007        | 26.7857 | 750  | 0.8299          | 0.3356    | 0.3318 |
| 0.0006        | 28.5714 | 800  | 0.8390          | 0.3344    | 0.3318 |
| 0.0004        | 30.3571 | 850  | 0.8442          | 0.3350    | 0.3323 |
| 0.0002        | 32.1429 | 900  | 0.8444          | 0.3307    | 0.3294 |
| 0.0005        | 33.9286 | 950  | 0.8549          | 0.3344    | 0.3329 |
| 0.0007        | 35.7143 | 1000 | 0.8515          | 0.3331    | 0.3329 |
| 0.0003        | 37.5    | 1050 | 0.8571          | 0.3263    | 0.3264 |
| 0.0005        | 39.2857 | 1100 | 0.8504          | 0.3307    | 0.3294 |
| 0.0001        | 41.0714 | 1150 | 0.8654          | 0.3313    | 0.3318 |
| 0.0005        | 42.8571 | 1200 | 0.8724          | 0.3337    | 0.3347 |
| 0.0001        | 44.6429 | 1250 | 0.8806          | 0.3325    | 0.3341 |
| 0.0001        | 46.4286 | 1300 | 0.8901          | 0.3344    | 0.3359 |
| 0.0001        | 48.2143 | 1350 | 0.8941          | 0.3344    | 0.3359 |
| 0.0001        | 50.0    | 1400 | 0.8987          | 0.3337    | 0.3353 |
| 0.0           | 51.7857 | 1450 | 0.9018          | 0.3337    | 0.3359 |
| 0.0           | 53.5714 | 1500 | 0.9073          | 0.3325    | 0.3353 |
| 0.0           | 55.3571 | 1550 | 0.9106          | 0.3319    | 0.3347 |
| 0.0           | 57.1429 | 1600 | 0.9152          | 0.3319    | 0.3347 |
| 0.0           | 58.9286 | 1650 | 0.9198          | 0.4824    | 0.4917 |
| 0.0           | 60.7143 | 1700 | 0.9242          | 0.4824    | 0.4923 |
| 0.0           | 62.5    | 1750 | 0.9279          | 0.4849    | 0.4947 |
| 0.0           | 64.2857 | 1800 | 0.9327          | 0.4855    | 0.4953 |
| 0.0           | 66.0714 | 1850 | 0.9374          | 0.4849    | 0.4953 |
| 0.0           | 67.8571 | 1900 | 0.9417          | 0.4855    | 0.4965 |
| 0.0           | 69.6429 | 1950 | 0.9461          | 0.4855    | 0.4965 |
| 0.0           | 71.4286 | 2000 | 0.9507          | 0.4855    | 0.4965 |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1