metadata
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-large-v3-finetuned-6
results: []
whisper-large-v3-finetuned-6
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: 0.1070
- Wer: 115.1997
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: 2e-07
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3572 | 1.0 | 7532 | 0.2604 | 105.7528 |
| 0.0008 | 2.0 | 15064 | 0.1888 | 99.7556 |
| 0.0001 | 3.0 | 22596 | 0.1495 | 106.2064 |
| 0.0 | 4.0 | 30128 | 0.1288 | 97.6591 |
| 0.0025 | 5.0 | 37660 | 0.1170 | 124.9313 |
| 0.0001 | 6.0 | 45192 | 0.1071 | 122.8575 |
| 0.0001 | 7.0 | 52724 | 0.1053 | 117.5784 |
| 0.0009 | 8.0 | 60256 | 0.1045 | 117.7447 |
| 0.0 | 9.0 | 67788 | 0.1058 | 118.8636 |
| 0.0003 | 10.0 | 75320 | 0.1070 | 115.1997 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2