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: 0.6249
- Wer: 73.7172
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: 4
- 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: linear
- lr_scheduler_warmup_steps: 312
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.2169 | 1.2698 | 40 | 1.7869 | 241.5580 |
| 1.0037 | 2.5397 | 80 | 0.8910 | 78.5521 |
| 0.5907 | 3.8095 | 120 | 0.6249 | 73.7172 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1