|
--- |
|
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: /content/zeon8985army/AllIndonesian-fineTunedLargeV2-id-1/checkpoint-192 |
|
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. --> |
|
|
|
# /content/zeon8985army/AllIndonesian-fineTunedLargeV2-id-1/checkpoint-192 |
|
|
|
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the IndonesianAll dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2235 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.7039 | 0.04 | 12 | 1.3824 | |
|
| 1.5534 | 0.08 | 24 | 1.1951 | |
|
| 1.0896 | 0.12 | 36 | 0.8549 | |
|
| 0.8805 | 0.16 | 48 | 0.6975 | |
|
| 0.7475 | 0.2 | 60 | 0.6245 | |
|
| 0.6436 | 0.25 | 72 | 0.5783 | |
|
| 0.606 | 0.29 | 84 | 0.5371 | |
|
| 0.5558 | 0.33 | 96 | 0.5013 | |
|
| 0.5116 | 0.37 | 108 | 0.4695 | |
|
| 0.491 | 0.41 | 120 | 0.4379 | |
|
| 0.4481 | 0.45 | 132 | 0.4017 | |
|
| 0.4029 | 0.49 | 144 | 0.3533 | |
|
| 0.3149 | 0.53 | 156 | 0.2834 | |
|
| 0.2592 | 0.57 | 168 | 0.2338 | |
|
| 0.2175 | 0.61 | 180 | 0.2311 | |
|
| 0.1989 | 0.66 | 192 | 0.2278 | |
|
| 0.2031 | 0.7 | 204 | 0.2263 | |
|
| 0.2256 | 0.74 | 216 | 0.2250 | |
|
| 0.2065 | 0.78 | 228 | 0.2245 | |
|
| 0.1916 | 0.82 | 240 | 0.2246 | |
|
| 0.2115 | 0.86 | 252 | 0.2242 | |
|
| 0.2135 | 0.9 | 264 | 0.2238 | |
|
| 0.2177 | 0.94 | 276 | 0.2235 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
