metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-tiny-hindi2_test
results: []
whisper-tiny-hindi2_test
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2043
- Wer: 27.6560
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: 3.75e-05
- train_batch_size: 16
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 50
- training_steps: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2449 | 1.2698 | 40 | 0.1597 | 25.8853 |
| 0.1002 | 2.5397 | 80 | 0.1644 | 26.6442 |
| 0.0492 | 3.8095 | 120 | 0.1730 | 27.0658 |
| 0.0269 | 5.0794 | 160 | 0.1801 | 26.9815 |
| 0.0156 | 6.3492 | 200 | 0.2043 | 27.6560 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1