Hugging Face's logo

krishna195
/
speecht5_hindi_local_krishna

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_hindi_local_krishna / README.md
krishna195's picture
krishna195
End of training
1c3f880 verified
preview code
|
raw
history blame contribute delete
1.69 kB
metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
model-index:
  - name: speecht5_hindi_local_krishna
    results: []

speecht5_hindi_local_krishna

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: 0.5305

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: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.8672 1.3468 100 0.7516
0.6743 2.6936 200 0.6181
0.6049 4.0404 300 0.5632
0.5735 5.3872 400 0.5389
0.5596 6.7340 500 0.5305

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.5.0+cu121
  • Datasets 3.0.2
  • Tokenizers 0.19.1