metadata
base_model: openai/whisper-tiny
license: apache-2.0
metrics:
- wer
tags:
- generated_from_trainer
model-index:
- name: whisper-tinyfinacialKI100
results: []
whisper-tinyfinacialKI100
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: 0.5053
- Wer: 46.0674
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: 1.35e-05
- 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: 100
- training_steps: 400
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.3759 | 50 | 0.9258 | 67.9775 |
| No log | 0.7519 | 100 | 0.7255 | 64.0449 |
| No log | 1.1278 | 150 | 0.5674 | 50.5618 |
| No log | 1.5038 | 200 | 0.5488 | 49.4382 |
| No log | 1.8797 | 250 | 0.5293 | 49.4382 |
| No log | 2.2556 | 300 | 0.5152 | 46.6292 |
| No log | 2.6316 | 350 | 0.5011 | 43.8202 |
| No log | 3.0075 | 400 | 0.5053 | 46.0674 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1