metadata
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: w-train-medium-Punjabi-4-0-2000-1e-05-8-8-500
results: []
w-train-medium-Punjabi-4-0-2000-1e-05-8-8-500
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3046
- Bleu: 29.3147
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu |
|---|---|---|---|---|
| 0.0564 | 3.18 | 500 | 1.0654 | 26.3435 |
| 0.0064 | 6.37 | 1000 | 1.1987 | 29.7507 |
| 0.0009 | 9.55 | 1500 | 1.2901 | 29.5279 |
| 0.0006 | 12.74 | 2000 | 1.3046 | 29.3147 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.0.0+cu117
- Datasets 2.14.6
- Tokenizers 0.14.1