kinkpunk's picture
Update README.md
5642429
metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
  - text-to-speech
datasets:
  - facebook/multilingual_librispeech
model-index:
  - name: speecht5_finetuned_librispeech_pl
    results: []

speecht5_finetuned_librispeech_pl

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

  • Loss: 0.3790

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: 3e-05
  • train_batch_size: 8
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • 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

Training results

Training Loss Epoch Step Validation Loss
0.4341 3.75 1000 0.3954
0.4166 7.5 2000 0.3866
0.4132 11.25 3000 0.3805
0.4078 15.0 4000 0.3790

Framework versions

  • Transformers 4.31.0
  • Pytorch 1.13.0+cu117
  • Datasets 2.13.1
  • Tokenizers 0.11.6