speecht5_finetuned_sip_ai_v4_globo_female

This model is a fine-tuned version of guilhermebastos96/speecht5_finetuned_sip_ai_v3 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3367

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
0.3933	7.14	1000	0.3580
0.3845	14.27	2000	0.3482
0.374	21.41	3000	0.3425
0.3774	28.55	4000	0.3405
0.365	35.68	5000	0.3393
0.3673	42.82	6000	0.3368
0.3659	49.96	7000	0.3387
0.3649	57.09	8000	0.3375
0.3618	64.23	9000	0.3374
0.3634	71.36	10000	0.3367

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.2.1
• Datasets 2.18.0
• Tokenizers 0.15.2