SpeechT5 TTS English Genshin

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

  • Loss: 0.5421

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: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.6689 1.9550 1000 0.5954
0.6139 3.9101 2000 0.5623
0.6054 5.8651 3000 0.5481
0.5932 7.8201 4000 0.5421

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.19.1
Downloads last month
13
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 SkylerChew/speecht5_tts_genshin

Finetuned
(856)
this model

Dataset used to train SkylerChew/speecht5_tts_genshin