Edit model card

SpeechT5 TTS hindi

This model is a fine-tuned version of microsoft/speecht5_tts on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4485

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: 16
  • eval_batch_size: 8
  • 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: 500
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.0737 16.2602 1000 0.4705
1.8856 32.5203 2000 0.4563
1.9033 48.7805 3000 0.4466
1.8761 65.0407 4000 0.4485

Framework versions

  • Transformers 4.46.0.dev0
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.20.1
Downloads last month
27
Safetensors
Model size
144M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Niha14/speecht5_tts_voxpopuli_hindi

Finetuned
(750)
this model

Dataset used to train Niha14/speecht5_tts_voxpopuli_hindi