README.md

metadata

language:
  - en
license: apache-2.0
base_model: openai/whisper-base
tags:
  - en-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_3_0
metrics:
  - wer
model-index:
  - name: Whisper base en - spongebob
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 3.0
          type: mozilla-foundation/common_voice_3_0
          args: 'config: en, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 18.36301062397127

Whisper base en - spongebob

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

• Loss: 0.3451
• Wer: 18.3630

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: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 1500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2586	0.84	500	0.3588	19.4733
0.1667	1.68	1000	0.3451	17.4892
0.1069	2.53	1500	0.3451	18.3630

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0