metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-tiny-en
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: 34.120425029515935
whisper-tiny-en
This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6900
- Wer Ortho: 35.9038
- Wer: 34.1204
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 150
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 3.5847 | 1.79 | 50 | 2.5796 | 52.3751 | 40.2597 |
| 0.6921 | 3.57 | 100 | 0.6884 | 42.5663 | 37.1901 |
| 0.305 | 5.36 | 150 | 0.5833 | 39.1733 | 35.5962 |
| 0.1133 | 7.14 | 200 | 0.5980 | 36.8291 | 34.3566 |
| 0.0391 | 8.93 | 250 | 0.6228 | 37.3843 | 34.2385 |
| 0.0138 | 10.71 | 300 | 0.6522 | 39.4201 | 37.1311 |
| 0.0051 | 12.5 | 350 | 0.6699 | 35.7187 | 33.4711 |
| 0.0032 | 14.29 | 400 | 0.6826 | 36.0888 | 34.0024 |
| 0.0027 | 16.07 | 450 | 0.6881 | 36.2122 | 34.3566 |
| 0.0024 | 17.86 | 500 | 0.6900 | 35.9038 | 34.1204 |
Framework versions
- Transformers 4.29.0.dev0
- Pytorch 2.0.0+cu117
- Datasets 2.11.0
- Tokenizers 0.13.3