|
--- |
|
license: apache-2.0 |
|
base_model: openai/whisper-tiny |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: whisper_syl_cv12_pad_lob100__0005 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information Keras had access to. You should |
|
probably proofread and complete it, then remove this comment. --> |
|
|
|
# whisper_syl_cv12_pad_lob100__0005 |
|
|
|
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 3.6239 |
|
- Train Accuracy: 0.0152 |
|
- Train Wermet: 0.7866 |
|
- Validation Loss: 3.0647 |
|
- Validation Accuracy: 0.0136 |
|
- Validation Wermet: 0.8282 |
|
- Epoch: 4 |
|
|
|
## 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: |
|
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01} |
|
- training_precision: float32 |
|
|
|
### Training results |
|
|
|
| Train Loss | Train Accuracy | Train Wermet | Validation Loss | Validation Accuracy | Validation Wermet | Epoch | |
|
|:----------:|:--------------:|:------------:|:---------------:|:-------------------:|:-----------------:|:-----:| |
|
| 5.0233 | 0.0115 | 1.6383 | 3.8616 | 0.0117 | 0.9516 | 0 | |
|
| 4.4412 | 0.0127 | 0.8560 | 3.5410 | 0.0125 | 0.8971 | 1 | |
|
| 4.0719 | 0.0138 | 0.8366 | 3.2944 | 0.0132 | 0.8706 | 2 | |
|
| 3.8091 | 0.0146 | 0.8133 | 3.1691 | 0.0134 | 0.8487 | 3 | |
|
| 3.6239 | 0.0152 | 0.7866 | 3.0647 | 0.0136 | 0.8282 | 4 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.0.dev0 |
|
- TensorFlow 2.13.0 |
|
- Tokenizers 0.13.3 |
|
|
