README.md

metadata

language:
  - ta
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - parambharat/tamil_asr_corpus
metrics:
  - wer
model-index:
  - name: Whisper medium english - Logii33-Tamil
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: ' asr corpus'
          type: parambharat/tamil_asr_corpus
          config: default
          split: test
          args: default
        metrics:
          - name: Wer
            type: wer
            value: 16.834654741982387

Whisper medium english - Logii33-Tamil

This model is a fine-tuned version of openai/whisper-medium on the asr corpus dataset. It achieves the following results on the evaluation set:

• Loss: 0.2995
• Wer Ortho: 54.6978
• Wer: 16.8347

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: 8
• eval_batch_size: 8
• 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: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.236	0.0088	500	0.2995	54.6978	16.8347

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1