speecht5_finetuned_roman_ur

This model is a fine-tuned version of EhsanElahi/speecht5_finetuned_voxpopuli_nl on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4980

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: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 1024
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 50
• training_steps: 100

Training results

Training Loss	Epoch	Step	Validation Loss
0.5267	13.56	50	0.4973
0.5245	27.12	100	0.4980

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3