metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-tiny
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: 0.6605667060212514
whisper-tiny
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: 0.7343
- Wer Ortho: 0.6730
- Wer: 0.6606
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: 5e-06
- 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: 600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.4699 | 3.57 | 100 | 0.6164 | 0.4695 | 0.4067 |
| 0.1623 | 7.14 | 200 | 0.5796 | 0.4275 | 0.3796 |
| 0.0399 | 10.71 | 300 | 0.6172 | 0.4528 | 0.4168 |
| 0.0082 | 14.29 | 400 | 0.6808 | 0.5262 | 0.5083 |
| 0.0027 | 17.86 | 500 | 0.7123 | 0.6422 | 0.6275 |
| 0.0016 | 21.43 | 600 | 0.7343 | 0.6730 | 0.6606 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.15.0