metadata
language:
- en
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: minds14
type: PolyAI/minds14
config: en-US
split: train
args: en-US
metrics:
- name: Wer
type: wer
value: 0.3612750885478158
pipeline_tag: automatic-speech-recognition
Whisper tiny
This model is a fine-tuned version of openai/whisper-tiny on the minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6491
- Wer Ortho: 0.3572
- Wer: 0.3613
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-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 8
- training_steps: 45
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.0569 | 0.2679 | 15 | 0.6113 | 0.3337 | 0.3294 |
| 0.0364 | 0.5357 | 30 | 0.6443 | 0.3603 | 0.3554 |
| 0.0916 | 0.8036 | 45 | 0.6491 | 0.3572 | 0.3613 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1