Whisper Large V2 Punjabi

🚀 Whisper Large Punjabi - Drishti Sharma

This model is a fine - tuned version of openai/whisper-large-v2, which can effectively perform automatic speech recognition tasks on the Punjabi language, achieving good performance on the Common Voice 11.0 dataset.

🚀 Quick Start

This model is a fine - tuned version of openai/whisper-large-v2 on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2846
• Wer: 19.7125

📚 Documentation

Model Information

Model Index

The model is named "Whisper Large Punjabi - Drishti Sharma", and the results are as follows:

• Task: Automatic Speech Recognition
• Dataset:
  • Name: Common Voice 11.0
  • Type: mozilla-foundation/common_voice_11_0
  • Config: pa - IN
  • Split: test
  • Args: pa - IN
• Metrics:
  • Name: Wer
  • Type: wer
  • Value: 19.71252566735113

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: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training Results

Framework Versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu116
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2

📄 License

This project is licensed under the Apache - 2.0 license.