Edit model card

ceb_b128_le3_s4000

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: 0.4401

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: 0.001
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2000
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.42 39.6040 500 0.4051
0.4187 79.2079 1000 0.4409
0.4401 118.8119 1500 0.4780
0.4456 158.4158 2000 0.4567
0.4221 198.0198 2500 0.4531
0.3571 237.6238 3000 0.4504
0.3287 277.2277 3500 0.4408
0.3154 316.8317 4000 0.4401

Framework versions

  • Transformers 4.41.0.dev0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
0
Safetensors
Model size
144M params
Tensor type
F32
·

Finetuned from