Hugging Face's logo

fahadqazi
/
Sindhi-TTS

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Sindhi-TTS / README.md
fahadqazi's picture
fahadqazi
Training in progress, step 4000
6168363 verified
preview code
|
raw
history blame
1.49 kB
metadata
library_name: transformers
license: mit
base_model: Sana1207/Hindi_SpeechT5_finetuned
tags:
  - generated_from_trainer
model-index:
  - name: Sindhi-TTS
    results: []

Sindhi-TTS

This model is a fine-tuned version of Sana1207/Hindi_SpeechT5_finetuned on the None dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.4860
  • eval_runtime: 91.8769
  • eval_samples_per_second: 19.396
  • eval_steps_per_second: 9.698
  • epoch: 15.9830
  • step: 4000

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: 16
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • 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: 100
  • training_steps: 5000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.5.0+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3