StefanJevtic63/whisper-large-v2-sr-lora

Whisper - Serbian Model

This model is a fine-tuned version of openai/whisper-large-v2 on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4203

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: 0.001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.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: 50
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.065	4.6189	1000	0.2782
0.0152	9.2379	2000	0.3293
0.0017	13.8568	3000	0.3778
0.0006	18.4758	4000	0.4203

Framework versions

• PEFT 0.13.2
• Transformers 4.46.3
• Pytorch 2.5.1
• Datasets 3.0.0
• Tokenizers 0.20.3