madhabpaul/tts-speecht5-asm

SpeechT5 TTS Assamese

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

• Loss: 0.4490

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: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• 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: 200
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5553	16.0	200	0.4852
0.5026	32.0	400	0.4547
0.4595	48.0	600	0.4444
0.464	64.0	800	0.4472
0.4612	80.0	1000	0.4490

Framework versions

• Transformers 4.42.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1