metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-tiny-PolyAI-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: 0.33392963625521765
whisper-tiny-PolyAI-minds14
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: 0.5770
- Wer Ortho: 0.3441
- Wer: 0.3339
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: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 2.1657 | 1.0 | 28 | 1.5460 | 0.4913 | 0.4168 |
| 0.4751 | 2.0 | 56 | 0.5582 | 0.3872 | 0.3757 |
| 0.346 | 3.0 | 84 | 0.5050 | 0.3622 | 0.3518 |
| 0.2062 | 4.0 | 112 | 0.4995 | 0.3797 | 0.3661 |
| 0.1223 | 5.0 | 140 | 0.5165 | 0.3547 | 0.3435 |
| 0.069 | 6.0 | 168 | 0.5367 | 0.3516 | 0.3351 |
| 0.0311 | 7.0 | 196 | 0.5545 | 0.3741 | 0.3643 |
| 0.013 | 8.0 | 224 | 0.5766 | 0.3822 | 0.3661 |
| 0.0075 | 9.0 | 252 | 0.5770 | 0.3441 | 0.3339 |
| 0.0037 | 10.0 | 280 | 0.5977 | 0.3485 | 0.3423 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0
- Datasets 2.13.1
- Tokenizers 0.13.3