metadata
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: []
Whisper Small Persian
This model is a fine-tuned version of 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