|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: openai/whisper-small |
|
model-index: |
|
- name: Whisper-small-new |
|
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-small-new |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0020 |
|
|
|
## 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: 0.001 |
|
- train_batch_size: 6 |
|
- eval_batch_size: 6 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 50 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.1302 | 1.0 | 137 | 0.0964 | |
|
| 0.0897 | 2.0 | 274 | 0.0545 | |
|
| 0.0691 | 3.0 | 411 | 0.0396 | |
|
| 0.0482 | 4.0 | 548 | 0.0279 | |
|
| 0.0374 | 5.0 | 685 | 0.0174 | |
|
| 0.0189 | 6.0 | 822 | 0.0096 | |
|
| 0.0108 | 7.0 | 959 | 0.0063 | |
|
| 0.004 | 8.0 | 1096 | 0.0039 | |
|
| 0.0039 | 9.0 | 1233 | 0.0024 | |
|
| 0.0026 | 10.0 | 1370 | 0.0020 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.0 |
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
