VMadalina/whisper-large-test-music

Whisper Large Ro - VM3

This model is a fine-tuned version of openai/whisper-large on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1271
• Wer: 19.1998

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• 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: 100
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0554	0.1206	100	0.1900	26.7148
0.0588	0.2413	200	0.1866	42.6189
0.156	0.3619	300	0.1515	22.3330
0.1327	0.4825	400	0.1349	18.0598
0.1226	0.6031	500	0.1271	19.1998

Framework versions

• Transformers 4.50.1
• Pytorch 2.6.0+cu124
• Datasets 2.13.1
• Tokenizers 0.21.1