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 EN - Tamas Szilagyi
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: 0.3512396694214876
Whisper Tiny EN - Tamas Szilagyi
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: 0.5354
- Wer Ortho: 0.3603
- Wer: 0.3512
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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| No log | 0.54 | 15 | 0.5404 | 0.3646 | 0.3512 |
| 0.2486 | 1.07 | 30 | 0.5320 | 0.3664 | 0.3554 |
| 0.2486 | 1.61 | 45 | 0.5354 | 0.3603 | 0.3512 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.17.0
- Tokenizers 0.15.2