README.md

metadata

language:
  - bn
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 finetuned on Bengali
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 15
          type: mozilla-foundation/common_voice_15_0
          config: bn
          split: validation
          args: bn
        metrics:
          - name: Wer
            type: wer
            value: 33.68672144182348

Whisper Small finetuned on Bengali

This model is a fine-tuned version of openai/whisper-small on the Common Voice 15 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2886
• Wer Ortho: 66.3996
• Wer: 33.6867

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: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 200
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.5075	0.8	100	0.4573	77.5920	45.3485
0.257	1.6	200	0.2886	66.3996	33.6867

Framework versions

• Transformers 4.36.0
• Pytorch 2.0.0
• Datasets 2.15.0
• Tokenizers 0.15.0