metadata
library_name: transformers
language:
- id
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Small Id - Tiny - Test
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: id
split: None
args: 'config: id, split: test'
metrics:
- name: Wer
type: wer
value: 58.26771653543307
Whisper Small Id - Tiny - Test
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.2371
- Wer: 58.2677
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: 32
- eval_batch_size: 8
- 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: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.8373 | 0.0625 | 1 | 1.6351 | 93.3071 |
| 1.7614 | 0.125 | 2 | 1.5526 | 90.9449 |
| 1.5333 | 0.1875 | 3 | 1.4336 | 59.4488 |
| 1.5874 | 0.25 | 4 | 1.3667 | 59.4488 |
| 1.4808 | 0.3125 | 5 | 1.3238 | 58.2677 |
| 1.5046 | 0.375 | 6 | 1.2933 | 56.6929 |
| 1.3783 | 0.4375 | 7 | 1.2704 | 57.4803 |
| 1.3692 | 0.5 | 8 | 1.2536 | 57.0866 |
| 1.3708 | 0.5625 | 9 | 1.2426 | 57.0866 |
| 1.3299 | 0.625 | 10 | 1.2371 | 58.2677 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3