speecht5_clartts_finetuned_TTS-PLS

This model is a fine-tuned version of MBZUAI/speecht5_tts_clartts_ar on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6078

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-06
• 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: 4000

Training results

Training Loss	Epoch	Step	Validation Loss
0.725	2.8229	500	0.6835
0.6797	5.6457	1000	0.6435
0.6622	8.4686	1500	0.6273
0.6533	11.2915	2000	0.6208
0.6468	14.1143	2500	0.6134
0.6408	16.9372	3000	0.6108
0.6397	19.7601	3500	0.6106
0.64	22.5829	4000	0.6078

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1