Hugging Face's logo

kaushikpatriot
/
speecht5_finetuned_voxpopuli_it

Text-to-Audio
Transformers
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Community
speecht5_finetuned_voxpopuli_it / README.md
kaushikpatriot's picture
kaushikpatriot
End of training
f3b2c71 verified
preview code
|
raw
history blame contribute delete
1.58 kB
metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - voxpopuli
model-index:
  - name: speecht5_finetuned_voxpopuli_it
    results: []

speecht5_finetuned_voxpopuli_it

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: 0.5130

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: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5535 6.1303 1000 0.5130

Framework versions

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