|
--- |
|
library_name: transformers |
|
language: |
|
- ar |
|
license: apache-2.0 |
|
base_model: openai/whisper-tiny |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: Whisper tiny AR - BH |
|
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 tiny AR - BH |
|
|
|
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the quran-ayat-speech-to-text dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0060 |
|
- Wer: 0.0802 |
|
- Cer: 0.0316 |
|
|
|
## 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: 5e-06 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 25 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:| |
|
| 0.0065 | 1.0 | 391 | 0.0057 | 0.0744 | 0.0290 | |
|
| 0.0054 | 2.0 | 782 | 0.0056 | 0.0733 | 0.0285 | |
|
| 0.0046 | 3.0 | 1173 | 0.0057 | 0.0782 | 0.0298 | |
|
| 0.0033 | 4.0 | 1564 | 0.0058 | 0.0746 | 0.0280 | |
|
| 0.0046 | 5.0 | 1955 | 0.0061 | 0.0726 | 0.0280 | |
|
| 0.0032 | 6.0 | 2346 | 0.0064 | 0.0726 | 0.0278 | |
|
| 0.0013 | 7.0 | 2737 | 0.0067 | 0.0740 | 0.0296 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.47.0 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
