metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-tiny-english-minds14
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: PolyAI/minds14
type: PolyAI/minds14
metrics:
- name: Wer
type: wer
value: 0.35335917312661497
whisper-tiny-english-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: 0.7096
- Wer Ortho: 0.3520
- Wer: 0.3534
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_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.3391 | 3.45 | 100 | 0.5298 | 0.3506 | 0.3508 |
| 0.0475 | 6.9 | 200 | 0.5772 | 0.3560 | 0.3559 |
| 0.0046 | 10.34 | 300 | 0.6521 | 0.3546 | 0.3540 |
| 0.0014 | 13.79 | 400 | 0.6903 | 0.3506 | 0.3521 |
| 0.0009 | 17.24 | 500 | 0.7096 | 0.3520 | 0.3534 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0