metadata

language:
  - id
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_15_0
metrics:
  - wer
model-index:
  - name: Whisper Small Id - Dhani
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 15.0
          type: mozilla-foundation/common_voice_15_0
          config: id
          split: None
          args: 'config: id, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 40.903586399627386

Whisper Small Id - Dhani

This model is a fine-tuned version of openai/whisper-small on the Common Voice 15.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.6569
Wer: 40.9036

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: 8e-06
train_batch_size: 64
eval_batch_size: 32
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: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2799	7.6923	1000	0.5497	38.1509
0.0732	15.3846	2000	0.5844	38.1602
0.0257	23.0769	3000	0.6366	39.9348
0.0164	30.7692	4000	0.6569	40.9036

Framework versions

Transformers 4.40.2
Pytorch 2.2.1+cu121
Datasets 2.19.1
Tokenizers 0.19.1