Edit model card

fine_tuned

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: 0.4328

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: 2
  • 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: 500
  • training_steps: 2500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5769 8.77 250 0.5205
0.4998 17.54 500 0.4383
0.4637 26.32 750 0.4285
0.4488 35.09 1000 0.4298
0.4307 43.86 1250 0.4272
0.4309 52.63 1500 0.4245
0.4272 61.4 1750 0.4282
0.4204 70.18 2000 0.4317
0.4222 78.95 2250 0.4313
0.4354 87.72 2500 0.4328

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.1.0+cu121
  • Datasets 2.17.0
  • Tokenizers 0.15.2
Downloads last month
1
Safetensors
Model size
144M params
Tensor type
F32
·
Inference API
This model can be loaded on Inference API (serverless).

Finetuned from