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[450:]
args: en-US
metrics:
- name: Wer
type: wer
value: 0.3252656434474616
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: 0.8008
- Wer Ortho: 0.3523
- Wer: 0.3253
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: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 1.593 | 1.79 | 50 | 1.0054 | 0.5003 | 0.4185 |
| 0.3982 | 3.57 | 100 | 0.7250 | 0.4121 | 0.3554 |
| 0.2075 | 5.36 | 150 | 0.6898 | 0.4226 | 0.3518 |
| 0.0957 | 7.14 | 200 | 0.6909 | 0.4028 | 0.3371 |
| 0.0412 | 8.93 | 250 | 0.7296 | 0.3695 | 0.3300 |
| 0.0186 | 10.71 | 300 | 0.7522 | 0.3627 | 0.3270 |
| 0.008 | 12.5 | 350 | 0.7703 | 0.3584 | 0.3288 |
| 0.0049 | 14.29 | 400 | 0.7756 | 0.3553 | 0.3294 |
| 0.0032 | 16.07 | 450 | 0.7889 | 0.3516 | 0.3235 |
| 0.0023 | 17.86 | 500 | 0.8008 | 0.3523 | 0.3253 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3