metadata
language:
- eng
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- fyp
metrics:
- wer
model-index:
- name: Whisper Fine tuned Small
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Fyp Dataset
type: fyp
args: 'config: eng, split: test'
metrics:
- name: Wer
type: wer
value: 11.272359095511305
Whisper Fine tuned Small
This model is a fine-tuned version of openai/whisper-small on the Fyp Dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.1965
- Wer: 11.2724
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: 8
- 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: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 102
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1398 | 0.4 | 20 | 0.2211 | 13.1623 |
| 0.0941 | 0.8 | 40 | 0.2144 | 11.8124 |
| 0.048 | 1.2 | 60 | 0.1997 | 11.2386 |
| 0.0481 | 1.6 | 80 | 0.1979 | 11.3736 |
| 0.0337 | 2.0 | 100 | 0.1965 | 11.2724 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1