metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- lozgen
metrics:
- wer
model-index:
- name: whisper-medium-lozgen-combined-model
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: lozgen
type: lozgen
metrics:
- name: Wer
type: wer
value: 0.3825645865282529
whisper-medium-lozgen-combined-model
This model is a fine-tuned version of openai/whisper-medium on the lozgen dataset. It achieves the following results on the evaluation set:
- Loss: 0.7861
- Wer: 0.3826
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- 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: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.663 | 1.6024 | 200 | 0.9298 | 0.4814 |
| 0.5567 | 3.2008 | 400 | 0.7861 | 0.3826 |
| 0.2961 | 4.8032 | 600 | 0.7904 | 0.3852 |
| 0.0985 | 6.4016 | 800 | 0.8693 | 0.3512 |
| 0.0528 | 8.0 | 1000 | 0.8797 | 0.3478 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0