metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-tiny-ft-PolyAI-minds-14-enUS
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: 0.3689492325855962
whisper-tiny-ft-PolyAI-minds-14-enUS
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: 0.6365
- Wer Ortho: 0.3763
- Wer: 0.3689
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: 4e-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: 100
- training_steps: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 2.9861 | 0.89 | 25 | 1.7468 | 0.5219 | 0.4038 |
| 0.8551 | 1.79 | 50 | 0.5897 | 0.8075 | 0.7928 |
| 0.3477 | 2.68 | 75 | 0.5229 | 0.6206 | 0.6198 |
| 0.151 | 3.57 | 100 | 0.5565 | 0.6971 | 0.6895 |
| 0.0895 | 4.46 | 125 | 0.5740 | 0.4812 | 0.4752 |
| 0.0373 | 5.36 | 150 | 0.5987 | 0.4479 | 0.4416 |
| 0.0232 | 6.25 | 175 | 0.6463 | 0.3751 | 0.3660 |
| 0.015 | 7.14 | 200 | 0.6365 | 0.3763 | 0.3689 |
Framework versions
- Transformers 4.33.0
- Pytorch 1.12.1+cu116
- Datasets 2.14.4
- Tokenizers 0.12.1