metadata
library_name: transformers
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: 0.32762691853600945
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: 0.6637
- Wer Ortho: 0.3263
- Wer: 0.3276
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|---|---|
| 1.3521 | 1.7857 | 50 | 0.5871 | 0.4127 | 0.3849 |
| 0.2839 | 3.5714 | 100 | 0.4864 | 0.3356 | 0.3300 |
| 0.0983 | 5.3571 | 150 | 0.5188 | 0.3387 | 0.3270 |
| 0.0285 | 7.1429 | 200 | 0.5651 | 0.3282 | 0.3164 |
| 0.0064 | 8.9286 | 250 | 0.5842 | 0.3152 | 0.3123 |
| 0.0021 | 10.7143 | 300 | 0.6164 | 0.3313 | 0.3312 |
| 0.0013 | 12.5 | 350 | 0.6319 | 0.3263 | 0.3259 |
| 0.0009 | 14.2857 | 400 | 0.6441 | 0.3245 | 0.3235 |
| 0.0007 | 16.0714 | 450 | 0.6542 | 0.3251 | 0.3241 |
| 0.0006 | 17.8571 | 500 | 0.6637 | 0.3263 | 0.3276 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0