Hugging Face's logo

Asim037
/
lj_speech_asim

Text-to-Audio
Transformers
TensorBoard
Safetensors
English
speecht5
[finetuned_model, lj_speech11]
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
lj_speech_asim / README.md
Asim037's picture
Asim037
End of training
3306ed0 verified
preview code
|
raw
history blame
1.56 kB
metadata
language:
  - eng
license: mit
base_model: microsoft/speecht5_tts
tags:
  - '[finetuned_model, lj_speech]'
  - generated_from_trainer
datasets:
  - FYP/LJ-Speech
model-index:
  - name: SpeechT5 TTS
    results: []

SpeechT5 TTS

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

  • Loss: 0.9651

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: 100
  • training_steps: 200
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.3099 0.2714 100 1.1364
1.0547 0.5427 200 0.9651

Framework versions

  • Transformers 4.41.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1