metadata
language:
- fa
base_model: makhataei/Whisper-Small-Common-Voice
tags:
- fa-asr
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: Whisper Small Persian
results: []
Whisper Small Persian
This model is a fine-tuned version of makhataei/Whisper-Small-Common-Voice on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7188
- Wer: 45.7630
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-07
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 40
- 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 |
|---|---|---|---|---|
| 0.0078 | 0.02 | 10 | 0.7181 | 45.7538 |
| 0.0033 | 0.03 | 20 | 0.7180 | 45.8093 |
| 0.0007 | 0.05 | 30 | 0.7180 | 45.7861 |
| 0.0006 | 0.06 | 40 | 0.7182 | 45.7792 |
| 0.0007 | 0.08 | 50 | 0.7185 | 45.7653 |
| 0.0007 | 0.09 | 60 | 0.7187 | 45.7630 |
| 0.0006 | 0.11 | 70 | 0.7187 | 45.7653 |
| 0.0037 | 0.12 | 80 | 0.7187 | 45.7700 |
| 0.0007 | 0.14 | 90 | 0.7188 | 45.7607 |
| 0.0005 | 0.15 | 100 | 0.7188 | 45.7630 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0