metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
metrics:
- wer
model-index:
- name: whisper-tiny-minds14-en-us
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: 0.3382526564344746
whisper-tiny-minds14-en-us
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: 0.7795
- Wer Ortho: 0.3368
- Wer: 0.3383
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: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0007 | 17.8571 | 500 | 0.6344 | 0.3226 | 0.3253 |
| 0.0002 | 35.7143 | 1000 | 0.6878 | 0.3313 | 0.3335 |
| 0.0001 | 53.5714 | 1500 | 0.7186 | 0.3344 | 0.3359 |
| 0.0001 | 71.4286 | 2000 | 0.7409 | 0.3344 | 0.3359 |
| 0.0001 | 89.2857 | 2500 | 0.7565 | 0.3331 | 0.3347 |
| 0.0001 | 107.1429 | 3000 | 0.7684 | 0.3368 | 0.3383 |
| 0.0 | 125.0 | 3500 | 0.7763 | 0.3374 | 0.3388 |
| 0.0 | 142.8571 | 4000 | 0.7795 | 0.3368 | 0.3383 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1