metadata

library_name: transformers
language:
  - ps
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - pairsys/open_asr
metrics:
  - wer
model-index:
  - name: Whisper Small Pashto
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Open ASR
          type: pairsys/open_asr
          args: 'config: pashto'
        metrics:
          - name: Wer
            type: wer
            value: 34.475374732334046

Whisper Small Pashto

This model is a fine-tuned version of openai/whisper-small on the Open ASR dataset. It achieves the following results on the evaluation set:

Loss: 0.7846
Wer: 34.4754

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: 16
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0112	17.8571	1000	0.6265	38.1462
0.0023	35.7143	2000	0.7230	35.0260
0.0006	53.5714	3000	0.7555	34.7201
0.0001	71.4286	4000	0.7708	34.9342
0.0001	89.2857	5000	0.7846	34.4754

Framework versions

Transformers 4.46.2
Pytorch 2.5.1
Datasets 3.1.0
Tokenizers 0.20.3