Assamese_tts_mehdi

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

  • eval_loss: 0.5467
  • eval_runtime: 1.6918
  • eval_samples_per_second: 59.11
  • eval_steps_per_second: 7.684
  • epoch: 151.7368
  • step: 4400

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: 0.0002
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • 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: 200
  • num_epochs: 200
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.47.1
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0
Downloads last month
33
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 kingmhd1519/Assamese_tts_mehdi

Finetuned
(856)
this model