metadata
library_name: transformers
language:
- en
license: apache-2.0
base_model: openai/whisper-small.en
tags:
- generated_from_trainer
datasets:
- yezarniko/medicines-asr2
metrics:
- wer
model-index:
- name: Pharmacy ASR Whisper Base Model
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Medicines ASR Dataset
type: yezarniko/medicines-asr2
args: 'config: en, split: test'
metrics:
- name: Wer
type: wer
value: 0
Pharmacy ASR Whisper Base Model
This model is a fine-tuned version of openai/whisper-small.en on the Medicines ASR Dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.0001
- Wer: 0.0
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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.035 | 1.0905 | 1000 | 0.0312 | 6.5282 |
| 0.0042 | 2.1810 | 2000 | 0.0018 | 0.5935 |
| 0.0083 | 3.2715 | 3000 | 0.0007 | 0.0 |
| 0.0003 | 4.3621 | 4000 | 0.0001 | 0.0 |
| 0.0002 | 5.4526 | 5000 | 0.0001 | 0.0 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.2