metadata

library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
model-index:
  - name: tamil_tts
    results: []

tamil_tts

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: 1.7523

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: 40
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 80
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: 2
training_steps: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.2489	0.0023	2	1.9940
1.9457	0.0047	4	1.7523

Framework versions

Transformers 4.50.0.dev0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0