metadata

language:
  - hi
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small En 3
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 3.0
          type: mozilla-foundation/common_voice_11_0
          args: 'config: hi, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 103.04743574321344

Whisper Small En 3

This model is a fine-tuned version of openai/whisper-small on the Common Voice 3.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.5263
Wer: 103.0474

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: 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
0.7717	1.34	1000	0.3452	49.7815
0.4884	2.67	2000	0.3808	61.0810
0.4106	4.01	3000	0.4805	93.7648
0.2197	5.34	4000	0.5263	103.0474

Framework versions

Transformers 4.39.3
Pytorch 2.2.1+cu121
Datasets 2.18.0
Tokenizers 0.15.2