speecht5_finetuned_local_language_dataset_bn

This model is a fine-tuned version of microsoft/speecht5_tts on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6038

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: 50
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.8489	0.1675	100	0.7253
0.7415	0.3349	200	0.6669
0.6951	0.5024	300	0.6351
0.6798	0.6699	400	0.6267
0.6757	0.8373	500	0.6246
0.674	1.0048	600	0.6127
0.6728	1.1723	700	0.6087
0.6599	1.3398	800	0.6061
0.6527	1.5072	900	0.6048
0.6583	1.6747	1000	0.6038

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1