Hugging Face's logo

pranavdaware
/
speecht5_tts_marathi_train1

Text-to-Audio
Transformers
TensorBoard
Safetensors
Marathi
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_tts_marathi_train1 / README.md
pranavdaware's picture
pranavdaware
End of training
34a564a verified
preview code
|
raw
history blame contribute delete
1.83 kB
metadata
library_name: transformers
language:
  - mr
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - srija616/GC_marathi_large
model-index:
  - name: SpeechT5 TTS marathi train1
    results: []

SpeechT5 TTS marathi train1

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

  • Loss: 0.7604

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-06
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • 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: 50
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.0728 5.2632 100 0.9236
1.8554 10.5263 200 0.8116
1.7615 15.7895 300 0.7807
1.6881 21.0526 400 0.7641
1.6793 26.3158 500 0.7604

Framework versions

  • Transformers 4.46.0.dev0
  • Pytorch 2.5.0+cu121
  • Datasets 3.0.2
  • Tokenizers 0.20.1