metadata
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-base-cs-cv11-rir-vol-bckgnoise-lowshelf-mp3
results: []
whisper-base-cs-cv11-rir-vol-bckgnoise-lowshelf-mp3
This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3720
- Wer: 36.1126
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 |
|---|---|---|---|---|
| 0.663 | 1.44 | 1000 | 0.4620 | 45.0529 |
| 0.4758 | 2.89 | 2000 | 0.3914 | 38.3394 |
| 0.3063 | 4.33 | 3000 | 0.3759 | 36.7573 |
| 0.2793 | 5.78 | 4000 | 0.3720 | 36.1126 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0