finetune_v13

This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.625
• Wer: 110.4425

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: 16
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 5
• training_steps: 80
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
No log	10.0	10	0.6289	29.6903
No log	20.0	20	0.6104	29.9558
No log	30.0	30	0.6177	33.8053
No log	40.0	40	0.6196	153.0973
0.1863	50.0	50	0.6226	89.8673
0.1863	60.0	60	0.6245	122.7876
0.1863	70.0	70	0.6255	99.6903
0.1863	80.0	80	0.625	110.4425

Framework versions

• Transformers 4.42.4
• Pytorch 2.2.0
• Datasets 2.20.0
• Tokenizers 0.19.1