metadata
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-base-atcosim
results: []
whisper-base-atcosim
This model is a fine-tuned version of openai/whisper-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: nan
- Wer: 100.8983
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-05
- train_batch_size: 16
- 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: 10
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0 | 0.01 | 5 | nan | 100.8983 |
| 0.0 | 0.02 | 10 | nan | 100.8983 |
| 0.0 | 0.03 | 15 | nan | 100.8983 |
| 0.0 | 0.04 | 20 | nan | 100.8983 |
| 0.0 | 0.05 | 25 | nan | 100.8983 |
| 0.0 | 0.06 | 30 | nan | 100.8983 |
| 0.0 | 0.07 | 35 | nan | 100.8983 |
| 0.0 | 0.08 | 40 | nan | 100.8983 |
| 0.0 | 0.09 | 45 | nan | 100.8983 |
| 0.0 | 0.1 | 50 | nan | 100.8983 |
| 0.0 | 0.12 | 55 | nan | 100.8983 |
| 0.0 | 0.13 | 60 | nan | 100.8983 |
| 0.0 | 0.14 | 65 | nan | 100.8983 |
| 0.0 | 0.15 | 70 | nan | 100.8983 |
| 0.0 | 0.16 | 75 | nan | 100.8983 |
| 0.0 | 0.17 | 80 | nan | 100.8983 |
| 0.0 | 0.18 | 85 | nan | 100.8983 |
| 0.0 | 0.19 | 90 | nan | 100.8983 |
| 0.0 | 0.2 | 95 | nan | 100.8983 |
| 0.0 | 0.21 | 100 | nan | 100.8983 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.1.1
- Datasets 2.15.0
- Tokenizers 0.13.3