metadata
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
model-index:
- name: Whisper-medium-Arabic-phoneme
results: []
Whisper-medium-Arabic-phoneme
This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2165
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: 0.001
- 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: 50
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0978 | 1.0 | 205 | 0.2293 |
| 0.0401 | 2.0 | 410 | 0.1967 |
| 0.0265 | 3.0 | 615 | 0.1954 |
| 0.0293 | 4.0 | 820 | 0.2346 |
| 0.0122 | 5.0 | 1025 | 0.2172 |
| 0.0117 | 6.0 | 1230 | 0.2048 |
| 0.0057 | 7.0 | 1435 | 0.2086 |
| 0.0034 | 8.0 | 1640 | 0.2014 |
| 0.0011 | 9.0 | 1845 | 0.2135 |
| 0.0003 | 10.0 | 2050 | 0.2165 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0