metadata
language:
- fa
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation-common-voice-17-0
metrics:
- wer
model-index:
- name: Whisper Small Persian - Persian ASR
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common-voice-17-0
type: mozilla-foundation-common-voice-17-0
config: default
split: test[:20%]
args: 'config: Persian, split: train[:20%]+validation[:20%]'
metrics:
- name: Wer
type: wer
value: 43.69646680942184
Whisper Small Persian - Persian ASR
This model is a fine-tuned version of openai/whisper-small on the common-voice-17-0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6543
- Wer: 43.6965
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-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3355 | 1.0 | 1973 | 0.5819 | 50.9101 |
| 0.176 | 2.0 | 3946 | 0.5479 | 49.8796 |
| 0.0767 | 3.0 | 5919 | 0.5610 | 45.3292 |
| 0.0262 | 4.0 | 7892 | 0.6115 | 44.0645 |
| 0.0116 | 5.0 | 9865 | 0.6543 | 43.6965 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1