metadata

license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - common_voice_17_0
metrics:
  - wer
model-index:
  - name: whisper-small-fa
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_17_0
          type: common_voice_17_0
          config: fa
          split: test
          args: fa
        metrics:
          - name: Wer
            type: wer
            value: 33.564735887399245

whisper-small-fa

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: 0.6225
Wer: 33.5647

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: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 30000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0145	4.0552	10000	0.4324	35.2682
0.0006	8.1103	20000	0.5496	33.7229
0.0001	12.1655	30000	0.6225	33.5647

Framework versions

Transformers 4.43.3
Pytorch 2.4.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1