speecht5-ft-voxpopuli-nl

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

  • Loss: 0.4540

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

Training results

Training Loss Epoch Step Validation Loss
0.5096 8.6 1000 0.4712
0.4863 17.2 2000 0.4594
0.4876 25.81 3000 0.4565
0.4791 34.41 4000 0.4540

Framework versions

  • Transformers 4.39.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1
Downloads last month
12
Safetensors
Model size
144M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for BanUrsus/speecht5-ft-voxpopuli-nl

Finetuned
(855)
this model