finetune_v8

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: 0.4224
• Wer: 102.2241

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	0.5239	19.1617
No log	20.0	20	0.4346	18.0496
No log	30.0	30	0.4050	17.1942
No log	40.0	40	0.4204	18.4773
0.0997	50.0	50	0.4294	20.6159
0.0997	60.0	60	0.4282	19.6749
0.0997	70.0	70	0.4246	23.9521
0.0997	80.0	80	0.4224	102.2241

Framework versions

• Transformers 4.42.3
• Pytorch 2.2.0
• Datasets 2.20.0
• Tokenizers 0.19.1