metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-tiny_yosthingalindo
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: PolyAI/minds14
type: PolyAI/minds14
metrics:
- name: Wer
type: wer
value: 0.33530106257378983
whisper-tiny_yosthingalindo
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: 0.5824
- Wer Ortho: 0.3424
- Wer: 0.3353
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: 250
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.3677 | 1.72 | 50 | 0.5198 | 0.3849 | 0.3648 |
| 0.1925 | 3.45 | 100 | 0.5038 | 0.3671 | 0.3518 |
| 0.0836 | 5.17 | 150 | 0.5206 | 0.3547 | 0.3406 |
| 0.0265 | 6.9 | 200 | 0.5520 | 0.3627 | 0.3518 |
| 0.008 | 8.62 | 250 | 0.5824 | 0.3424 | 0.3353 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.13.3