EvgenyShivchenkoUIT/speecht5_finetuned_gcr_2

TTS SpeechT5 GCR

This model is a fine-tuned version of 1aurent/speecht5_finetuned_fleurs_fr on the GuianeseCreole dataset. It achieves the following results on the evaluation set:

• Loss: 0.4406

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• training_steps: 900
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5127	3.4622	100	0.4955
0.494	6.9244	200	0.4817
0.4695	10.3556	300	0.4745
0.4726	13.8178	400	0.4721
0.4557	17.2489	500	0.4676
0.4538	20.7111	600	0.4455
0.4434	24.1422	700	0.4471
0.444	27.6044	800	0.4413
0.4395	31.0356	900	0.4406

Framework versions

• Transformers 4.52.0
• Pytorch 2.11.0+cu128
• Datasets 3.6.0
• Tokenizers 0.21.4