metadata
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-large-v3-finetuned-4
results: []
whisper-large-v3-finetuned-4
This model is a fine-tuned version of openai/whisper-large-v3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2707
- Wer: 84.5725
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: 5e-08
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.8473 | 1.0 | 7532 | 0.3636 | 69.4836 |
| 0.0229 | 2.0 | 15064 | 0.3078 | 54.1681 |
| 3.1078 | 3.0 | 22596 | 0.2848 | 67.0070 |
| 0.0011 | 4.0 | 30128 | 0.2737 | 75.4447 |
| 0.0001 | 5.0 | 37660 | 0.2707 | 84.5725 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2