speecht5_finetuned_sip_ai_v3

This model is a fine-tuned version of guilhermebastos96/speecht5_finetuned_sip_ai_v2 on the multilingual_librispeech dataset. It achieves the following results on the evaluation set:

• Loss: 0.3439

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: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 10000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.3996	1.68	1000	0.3638
0.3885	3.35	2000	0.3554
0.3785	5.03	3000	0.3508
0.3764	6.71	4000	0.3488
0.3732	8.38	5000	0.3485
0.3806	10.06	6000	0.3460
0.3739	11.74	7000	0.3454
0.3703	13.41	8000	0.3458
0.3732	15.09	9000	0.3445
0.3695	16.76	10000	0.3439

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2