metadata
base_model: openai/whisper-tiny
license: apache-2.0
metrics:
- wer
tags:
- generated_from_trainer
model-index:
- name: whisper-tinyfinacial2
results: []
whisper-tinyfinacial2
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: 0.8030
- Wer: 77.5281
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: 16
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 4.3478 | 100 | 0.7238 | 66.2921 |
| No log | 8.6957 | 200 | 0.6535 | 66.2921 |
| No log | 13.0435 | 300 | 0.7427 | 71.3483 |
| No log | 17.3913 | 400 | 0.7814 | 78.0899 |
| 0.3492 | 21.7391 | 500 | 0.7969 | 77.5281 |
| 0.3492 | 26.0870 | 600 | 0.8030 | 77.5281 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1