metadata

library_name: transformers
language:
  - en
license: apache-2.0
base_model: openai/whisper-base
tags:
  - generated_from_trainer
datasets:
  - atulksingh/mypin-voice-dataset
metrics:
  - wer
model-index:
  - name: Whisper Base myPin
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Domain Based voice
          type: atulksingh/mypin-voice-dataset
          config: default
          split: None
          args: 'split: test'
        metrics:
          - name: Wer
            type: wer
            value: 3.9215686274509802

Whisper Base myPin

This model is a fine-tuned version of openai/whisper-base on the Domain Based voice dataset. It achieves the following results on the evaluation set:

Loss: 0.0078
Wer: 3.9216

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: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
training_steps: 1500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0007	100.0	500	0.0086	3.9216
0.0003	200.0	1000	0.0079	3.9216
0.0002	300.0	1500	0.0078	3.9216

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.0
Tokenizers 0.19.1