speecht5_finetuned_en64_lr301

This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4580

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: 0.0001
• train_batch_size: 32
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 512
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 1500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4634	55.1724	100	0.3961
0.3883	110.3448	200	0.3942
0.3614	165.5172	300	0.4229
0.3456	220.6897	400	0.4271
0.3355	275.8621	500	0.4273
0.3257	331.0345	600	0.4478
0.3194	386.2069	700	0.4437
0.3116	441.3793	800	0.4586
0.3053	496.5517	900	0.4518
0.2994	551.7241	1000	0.4535
0.2969	606.8966	1100	0.4594
0.2946	662.0690	1200	0.4521
0.2904	717.2414	1300	0.4569
0.2889	772.4138	1400	0.4573
0.2911	827.5862	1500	0.4580

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1