riteshkr/quantized-whisper-large-v3

whisper-large-v3-quantized

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

• eval_loss: 1.1612
• eval_wer: 0.5591
• eval_runtime: 676.1374
• eval_samples_per_second: 0.602
• eval_steps_per_second: 0.075
• epoch: 0.4917
• step: 800

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: 1
• 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: 500
• training_steps: 1000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.43.3
• Pytorch 2.4.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1