|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: openai/whisper-large-v3 |
|
model-index: |
|
- name: Whisper-large-v3-Arabic-phoneme |
|
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-large-v3-Arabic-phoneme |
|
|
|
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2304 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.0416 | 1.0 | 546 | 0.2269 | |
|
| 0.0243 | 2.0 | 1092 | 0.2054 | |
|
| 0.0262 | 3.0 | 1638 | 0.1866 | |
|
| 0.009 | 4.0 | 2184 | 0.2000 | |
|
| 0.0196 | 5.0 | 2730 | 0.1928 | |
|
| 0.0071 | 6.0 | 3276 | 0.2099 | |
|
| 0.0054 | 7.0 | 3822 | 0.2070 | |
|
| 0.0066 | 8.0 | 4368 | 0.2189 | |
|
| 0.0006 | 9.0 | 4914 | 0.2325 | |
|
| 0.001 | 10.0 | 5460 | 0.2304 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
