Optimized Whisper Small Id for Inspirasi

This model is a fine-tuned version of openai/whisper-small on the Extracted Youtube with CommonVoice11, Fleurs, OpenSLR, and MagicData dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.3722
• eval_wer: 20.3324
• eval_runtime: 495.0068
• eval_samples_per_second: 3.527
• eval_steps_per_second: 0.222
• epoch: 3.0354
• step: 9000

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: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 10000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.49.0
• Pytorch 2.2.0a0+81ea7a4
• Datasets 3.3.2
• Tokenizers 0.21.0