metadata
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-tiny-khmer
results: []
whisper-tiny-khmer
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: 2.4574
- Wer: 1.4939
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: 6.25e-06
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- training_steps: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.0 | 1 | 3.0351 | 1.4989 |
| 3.6663 | 0.01 | 2 | 2.8513 | 1.5283 |
| 3.6663 | 0.01 | 3 | 2.6387 | 1.4964 |
| 3.6138 | 0.01 | 4 | 2.5656 | 1.5394 |
| 3.6138 | 0.01 | 5 | 2.5272 | 1.5169 |
| 3.1887 | 0.02 | 6 | 2.4940 | 1.5016 |
| 3.1887 | 0.02 | 7 | 2.4701 | 1.4778 |
| 3.052 | 0.02 | 8 | 2.4574 | 1.4939 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.6.dev0
- Tokenizers 0.14.1