|
--- |
|
base_model: openai/whisper-small |
|
datasets: |
|
- clt013/malay-speech-3k-rows-dataset_v2 |
|
language: |
|
- ms |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Whisper Small FT Malay - CLT013 |
|
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 FT Malay - CLT013 |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co./openai/whisper-small) on the Malay Speech 3k dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6336 |
|
|
|
## 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: 8 |
|
- 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: 100 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.1001 | 0.3731 | 100 | 0.8407 | |
|
| 0.7305 | 0.7463 | 200 | 0.7879 | |
|
| 0.615 | 1.1194 | 300 | 0.7401 | |
|
| 0.4364 | 1.4925 | 400 | 0.7126 | |
|
| 0.3951 | 1.8657 | 500 | 0.6772 | |
|
| 0.2428 | 2.2388 | 600 | 0.6649 | |
|
| 0.185 | 2.6119 | 700 | 0.6426 | |
|
| 0.1781 | 2.9851 | 800 | 0.6336 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.13.1.dev0 |
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.19.1 |
