speecht5_finetuned_eng_ashish

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

  • Loss: 0.7111

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: 0.0001
  • 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: 1
  • training_steps: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
No log 0.0602 1 0.7250
5.9911 0.1203 2 1.1100
5.9911 0.1805 3 0.8121
6.7456 0.2406 4 0.7525
6.7456 0.3008 5 0.7550
6.1898 0.3609 6 0.7549
6.1898 0.4211 7 0.7394
5.7588 0.4812 8 0.7304
5.7588 0.5414 9 0.7182
5.2002 0.6015 10 0.7111

Framework versions

  • Transformers 4.47.1
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0
Downloads last month
5
Safetensors
Model size
144M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for Ashish24032003/speecht5_finetuned_eng_ashish

Finetuned
(993)
this model