README.md

metadata

language:
  - en
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - generated_from_trainer
datasets:
  - Prajwal-143/ASR-Tamil-cleaned
metrics:
  - wer
model-index:
  - name: Whisper-large-v3-en-Log-Tamil
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: ' asr-tamil-cleaned'
          type: Prajwal-143/ASR-Tamil-cleaned
        metrics:
          - name: Wer
            type: wer
            value: 192.45811803270485

Whisper-large-v3-en-Log-Tamil

This model is a fine-tuned version of openai/whisper-large-v3 on the asr-tamil-cleaned dataset. It achieves the following results on the evaluation set:

• Loss: 0.1601
• Wer Ortho: 99.7086
• Wer: 192.4581

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
0.1482	0.0143	500	0.1601	99.7086	192.4581

Framework versions

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