whisper-large-fa-v1 / README.md
vhdm's picture
End of training
86599fc verified
|
raw
history blame
2.2 kB
metadata
library_name: transformers
language:
  - fa
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
  - generated_from_trainer
datasets:
  - vhdm/persian-voice-v1.1
metrics:
  - wer
model-index:
  - name: vhdm/whisper-v3-turbo-persian-v1.1
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: vhdm/persian-voice-v1
          type: vhdm/persian-voice-v1.1
          args: 'config: fa, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 14.065335753176045

vhdm/whisper-v3-turbo-persian-v1.1

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the vhdm/persian-voice-v1 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1445
  • Wer: 14.0653

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
0.219 0.6150 1000 0.2093 22.0750
0.1191 1.2300 2000 0.1698 17.8463
0.1051 1.8450 3000 0.1485 15.7895
0.0644 2.4600 4000 0.1530 16.0375
0.0289 3.0750 5000 0.1445 14.0653

Framework versions

  • Transformers 4.52.4
  • Pytorch 2.7.1+cu118
  • Datasets 3.6.0
  • Tokenizers 0.21.1