|
--- |
|
language: |
|
- nan |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: openai/whisper-small |
|
datasets: |
|
- mozilla-foundation/common_voice_16_1 |
|
model-index: |
|
- name: Whisper small Taiwanese - LoRA |
|
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 Taiwanese - LoRA |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3965 |
|
|
|
## 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: 16 |
|
- 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: 600 |
|
- num_epochs: 8 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 0.6127 | 1.0 | 1550 | 0.5854 | |
|
| 0.4298 | 2.0 | 3100 | 0.4626 | |
|
| 0.2312 | 3.0 | 4650 | 0.4104 | |
|
| 0.1738 | 4.0 | 6200 | 0.4112 | |
|
| 0.1321 | 5.0 | 7750 | 0.3960 | |
|
| 0.0898 | 6.0 | 9300 | 0.4087 | |
|
| 0.0652 | 7.0 | 10850 | 0.3947 | |
|
| 0.0341 | 8.0 | 12400 | 0.3965 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.1.dev0 |
|
- Transformers 4.38.1 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.1.dev0 |
|
- Tokenizers 0.15.2 |
