README.md

metadata

language:
  - eng
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 eng - Himanshu
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: NPTEL Sample dataset
          type: mozilla-foundation/common_voice_11_0
          args: 'config: eng, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 17.920937042459737

Whisper Small eng - Himanshu

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

• Loss: 0.5925
• Wer: 17.9209

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
0.0014	20.0	1000	0.5083	17.6574
0.0008	40.0	2000	0.5600	18.1552
0.0002	60.0	3000	0.5837	17.8917
0.0002	80.0	4000	0.5925	17.9209

Framework versions

• Transformers 4.43.3
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1