|
--- |
|
language: |
|
- id |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- id-asr-leaderboard |
|
- generated_from_trainer |
|
datasets: |
|
- '-' |
|
base_model: openai/whisper-large-v2 |
|
model-index: |
|
- name: zeon8985army/KhalsuuTagalog-fineTunedLargeV2-tl-1 |
|
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. --> |
|
|
|
# zeon8985army/KhalsuuTagalog-fineTunedLargeV2-tl-1 |
|
|
|
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the AlistairBegg dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2708 |
|
|
|
## 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: 6e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 12 |
|
- training_steps: 276 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 3.26 | 0.05 | 12 | 3.5752 | |
|
| 2.9122 | 0.1 | 24 | 2.9222 | |
|
| 2.1061 | 0.15 | 36 | 1.9585 | |
|
| 1.6265 | 0.2 | 48 | 1.5771 | |
|
| 1.3155 | 0.25 | 60 | 1.3177 | |
|
| 1.1793 | 0.3 | 72 | 1.1780 | |
|
| 1.0208 | 0.35 | 84 | 1.0613 | |
|
| 0.9111 | 0.4 | 96 | 0.9361 | |
|
| 0.8078 | 0.44 | 108 | 0.7634 | |
|
| 0.6103 | 0.49 | 120 | 0.4794 | |
|
| 0.3911 | 0.54 | 132 | 0.2857 | |
|
| 0.324 | 0.59 | 144 | 0.2915 | |
|
| 0.3228 | 0.64 | 156 | 0.2858 | |
|
| 0.3103 | 0.69 | 168 | 0.2778 | |
|
| 0.3458 | 0.74 | 180 | 0.2750 | |
|
| 0.3283 | 0.79 | 192 | 0.2738 | |
|
| 0.394 | 0.84 | 204 | 0.2728 | |
|
| 0.3181 | 0.89 | 216 | 0.2711 | |
|
| 0.3201 | 0.94 | 228 | 0.2704 | |
|
| 0.3291 | 0.99 | 240 | 0.2705 | |
|
| 0.3084 | 1.04 | 252 | 0.2709 | |
|
| 0.32 | 1.09 | 264 | 0.2711 | |
|
| 0.363 | 1.14 | 276 | 0.2708 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
