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-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: 0.3087367178276269
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: 0.4924
- Wer Ortho: 0.3085
- Wer: 0.3087
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: 3e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| No log | 1.0 | 4 | 3.6562 | 0.5416 | 0.4014 |
| No log | 2.0 | 8 | 2.3152 | 0.5170 | 0.4103 |
| No log | 3.0 | 12 | 1.1184 | 0.4201 | 0.3949 |
| No log | 4.0 | 16 | 0.5754 | 0.3979 | 0.3949 |
| No log | 5.0 | 20 | 0.5133 | 0.3812 | 0.3813 |
| No log | 6.0 | 24 | 0.4916 | 0.3455 | 0.3459 |
| 1.5902 | 7.0 | 28 | 0.4872 | 0.3504 | 0.3501 |
| 1.5902 | 8.0 | 32 | 0.4887 | 0.3325 | 0.3323 |
| 1.5902 | 9.0 | 36 | 0.4907 | 0.3146 | 0.3152 |
| 1.5902 | 10.0 | 40 | 0.4924 | 0.3085 | 0.3087 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1