|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- wer |
|
|
model-index: |
|
|
- name: whisper-tiny-hi2_test |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# whisper-tiny-hi2_test |
|
|
|
|
|
This model was trained from scratch on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.5037 |
|
|
- Wer: 58.3150 |
|
|
|
|
|
## 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: 3.75e-05 |
|
|
- train_batch_size: 32 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: constant |
|
|
- lr_scheduler_warmup_steps: 50 |
|
|
- training_steps: 200 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
|
| 0.6803 | 1.25 | 40 | 0.6102 | 65.9441 | |
|
|
| 0.3649 | 2.5 | 80 | 0.5037 | 58.3150 | |
|
|
| 0.2296 | 3.75 | 120 | 0.4897 | 66.7146 | |
|
|
| 0.1564 | 5.0 | 160 | 0.5131 | 65.3429 | |
|
|
| 0.0905 | 6.25 | 200 | 0.5504 | 63.9035 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.41.1 |
|
|
- Pytorch 2.3.1+cu121 |
|
|
- Datasets 2.19.1 |
|
|
- Tokenizers 0.19.1 |
|
|
|
