metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- common_voice_17_0
metrics:
- wer
model-index:
- name: whisper-small-test
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_17_0
type: common_voice_17_0
config: uz
split: None
args: uz
metrics:
- name: Wer
type: wer
value: 32.280771822969974
whisper-small-test
This model is a fine-tuned version of openai/whisper-small on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3346
- Wer: 32.2808
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: 8
- seed: 42
- optimizer: Use OptimizerNames.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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.5745 | 0.1088 | 1000 | 0.5290 | 45.9187 |
| 0.4554 | 0.2176 | 2000 | 0.4041 | 37.0572 |
| 0.3897 | 0.3264 | 3000 | 0.3553 | 33.9258 |
| 0.3655 | 0.4353 | 4000 | 0.3346 | 32.2808 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3