JET2001/speecht5_tts_imda_nsc_p1

Speech T5 TTS English

This model is a fine-tuned version of microsoft/speecht5_tts on the IMDA National Speech Corpus dataset. It achieves the following results on the evaluation set:

• Loss: 0.3968

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: 32
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 10.0
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4693	0.91	1000	0.4240
0.4524	1.82	2000	0.4132
0.4405	2.72	3000	0.4079
0.4416	3.63	4000	0.4056
0.4298	4.54	5000	0.4009
0.4363	5.45	6000	0.4002
0.4301	6.35	7000	0.3989
0.4376	7.26	8000	0.3978
0.4308	8.17	9000	0.3984
0.4363	9.08	10000	0.3971
0.4341	9.99	11000	0.3968

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0