Hugging Face's logo

Niha14
/
speecht5_tts_voxpopuli_hindi

Text-to-Speech
Transformers
TensorBoard
Safetensors
Hindi
speecht5
text-to-audio
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_tts_voxpopuli_hindi / README.md
Niha14's picture
Niha14
End of training
018012e verified
preview code
|
raw
history blame
1.79 kB
metadata
library_name: transformers
language:
  - hi
license: mit
base_model: microsoft/speecht5_tts
tags:
  - text-to-speech
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
model-index:
  - name: SpeechT5 TTS hindi
    results: []

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