Whisper Large V2 Ta

🚀 Whisper Large-v2 Tamil

This is a fine - tuned model based on openai/whisper - large - v2, specifically optimized for Tamil speech recognition, offering high - quality automatic speech recognition capabilities.

🚀 Quick Start

This model is a fine - tuned version of openai/whisper-large-v2 on the mozilla - foundation/common_voice_11_0 ta dataset. It achieves the following results on the evaluation set:

• Loss: 0.1727
• Wer: 8.4538

✨ Features

• Fine - Tuned: Based on the powerful openai/whisper-large-v2, fine - tuned for the Tamil language.
• Accurate Results: Achieves low loss and Wer on the evaluation set, demonstrating high performance in automatic speech recognition.

📚 Documentation

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

🔧 Technical Details

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e - 05
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• distributed_type: multi - GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e - 08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• training_steps: 1000

Training results

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2

📄 License

This project is licensed under the Apache - 2.0 license.