|
--- |
|
language: |
|
- fa |
|
license: apache-2.0 |
|
base_model: makhataei/Whisper-Small-Common-Voice |
|
tags: |
|
- fa-asr |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: Whisper Small Persian |
|
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 Persian |
|
|
|
This model is a fine-tuned version of [makhataei/Whisper-Small-Common-Voice](https://huggingface.co/makhataei/Whisper-Small-Common-Voice) on the Ctejarat dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5782 |
|
- Wer: 36.9283 |
|
|
|
## 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: 1e-06 |
|
- train_batch_size: 10 |
|
- eval_batch_size: 10 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 80 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 5 |
|
- training_steps: 100 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:| |
|
| 0.904 | 0.96 | 10 | 0.8973 | 46.7577 | |
|
| 0.7728 | 1.93 | 20 | 0.7814 | 42.3208 | |
|
| 0.6586 | 2.89 | 30 | 0.7098 | 40.3413 | |
|
| 0.586 | 3.86 | 40 | 0.6623 | 39.5904 | |
|
| 0.5336 | 4.82 | 50 | 0.6310 | 38.9078 | |
|
| 0.512 | 5.78 | 60 | 0.6091 | 37.6792 | |
|
| 0.4732 | 6.75 | 70 | 0.5945 | 37.6792 | |
|
| 0.4367 | 7.71 | 80 | 0.5851 | 37.2696 | |
|
| 0.4282 | 8.67 | 90 | 0.5800 | 37.0648 | |
|
| 0.4398 | 9.64 | 100 | 0.5782 | 36.9283 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
