whisper-small-dialect-classifier

This model is a fine-tuned version of yaygomii/whisper-small-ta-fyp on the Tamil-Speech-Dialect-Corpus-Shuffled-Split dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.1462
• eval_accuracy: 0.9713
• eval_runtime: 37.5749
• eval_samples_per_second: 28.796
• eval_steps_per_second: 1.81
• epoch: 10.0
• step: 5410

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.40.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2