whisper-large-v2-ft-my_dataset_snr0_owner12-241016

This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0000

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.2
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.714	0.8333	25	0.9943
0.2757	1.6667	50	0.0179
0.0077	2.5	75	0.0173
0.0055	3.3333	100	0.0027
0.0097	4.1667	125	0.0005
0.0	5.0	150	0.0043
0.0	5.8333	175	0.0000
0.0	6.6667	200	0.0000
0.0	7.5	225	0.0000
0.0	8.3333	250	0.0000
0.0	9.1667	275	0.0000
0.0	10.0	300	0.0000

Framework versions

• PEFT 0.13.0
• Transformers 4.45.0.dev0
• Pytorch 2.3.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1