Edit model card

fil_b64_le4_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: 0.4134

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: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • 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
0.4725 22.2222 500 0.4372
0.4415 44.4444 1000 0.4203
0.423 66.6667 1500 0.4169
0.4108 88.8889 2000 0.4183
0.3934 111.1111 2500 0.4111
0.3821 133.3333 3000 0.4164
0.3743 155.5556 3500 0.4127
0.3714 177.7778 4000 0.4134

Framework versions

  • Transformers 4.41.0.dev0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1
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