fazalazami/speecht5_finetuned_voxpopuli_nl

fazalazami-finetuned-testtospeech

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the facebook/voxpopuli dataset. It achieves the following results on the evaluation set:

• Loss: 0.4794

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: Use 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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.547	6.1303	1000	0.5015
0.5323	12.2605	2000	0.4867
0.522	18.3908	3000	0.4821
0.5127	24.5211	4000	0.4794

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3