AlexSolomon/speecht5_tts_finetune_ro

Romanian Colocvial Speech

This model is a fine-tuned version of IoanRazvan/speecht5_tts_voxpopuli_ro on the RomanianColocvialSpeech dataset. It achieves the following results on the evaluation set:

• Loss: 0.4040

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: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• 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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4604	11.3	1000	0.4145
0.4338	22.6	2000	0.4036
0.4305	33.9	3000	0.4070
0.4252	45.2	4000	0.4040

Framework versions

• Transformers 4.38.0.dev0
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2