Hugging Face's logo

Aumkeshchy2003
/
speecht5_finetuned_Aumkesh_tr

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_finetuned_Aumkesh_tr / README.md
Aumkeshchy2003's picture
Aumkeshchy2003
End of training
514f290 verified
preview code
|
raw
history blame contribute delete
1.75 kB
metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
model-index:
  - name: speecht5_finetuned_Aumkesh_tr
    results: []

speecht5_finetuned_Aumkesh_tr

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: 0.5056

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • training_steps: 600
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5789 3.2258 100 0.5092
0.5046 6.4516 200 0.4970
0.4729 9.6774 300 0.4971
0.4598 12.9032 400 0.4942
0.4442 16.1290 500 0.5118
0.4421 19.3548 600 0.5056

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.19.1