whisper-large-v2-ft-my_dataset_snr0_owner12_MPSENet-241016v2

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: 0.0019

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
4.0644	0.8621	25	1.0139
1.3619	1.7241	50	0.0809
0.0312	2.5862	75	0.0216
0.018	3.4483	100	0.0263
0.0063	4.3103	125	0.0191
0.0032	5.1724	150	0.0124
0.0004	6.0345	175	0.0092
0.0043	6.8966	200	0.0126
0.0	7.7586	225	0.0027
0.0	8.6207	250	0.0019
0.0	9.4828	275	0.0019

Framework versions

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