metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- swagen
metrics:
- wer
model-index:
- name: whisper-medium-swagen-female-5hrs-42
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: swagen
type: swagen
metrics:
- name: Wer
type: wer
value: 0.35986892829606787
whisper-medium-swagen-female-5hrs-42
This model is a fine-tuned version of openai/whisper-medium on the swagen dataset. It achieves the following results on the evaluation set:
- Loss: 0.5201
- Wer: 0.3599
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- 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 |
|---|---|---|---|---|
| 0.7077 | 0.4700 | 200 | 0.8156 | 0.5322 |
| 0.4582 | 0.9401 | 400 | 0.6325 | 0.4322 |
| 0.2709 | 1.4089 | 600 | 0.5872 | 0.4158 |
| 0.3208 | 1.8790 | 800 | 0.5507 | 0.3207 |
| 0.1102 | 2.3478 | 1000 | 0.5514 | 0.3261 |
| 0.1175 | 2.8179 | 1200 | 0.5201 | 0.3599 |
| 0.0483 | 3.2867 | 1400 | 0.5554 | 0.3178 |
| 0.0646 | 3.7568 | 1600 | 0.5444 | 0.3277 |
| 0.019 | 4.2256 | 1800 | 0.5775 | 0.3082 |
| 0.0237 | 4.6957 | 2000 | 0.5723 | 0.3346 |
Framework versions
- Transformers 4.53.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.0