Hugging Face's logo

JET2001
/
speecht5_tts_imda_nsc_p1_p3_v2

Text-to-Audio
Transformers
TensorBoard
Safetensors
English
speecht5
.
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_tts_imda_nsc_p1_p3_v2 / README.md
JET2001's picture
JET2001
End of training
3f95c43 verified
preview code
|
raw
history blame contribute delete
1.46 kB
metadata
language:
  - en
license: mit
base_model: microsoft/speecht5_tts
tags:
  - .
  - generated_from_trainer
datasets:
  - speecht5_imda_nsc_p1_p3
model-index:
  - name: Speech T5 TTS English
    results: []

Speech T5 TTS English

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

  • eval_loss: 0.3551
  • eval_runtime: 236.1173
  • eval_samples_per_second: 66.962
  • eval_steps_per_second: 2.096
  • epoch: 5.97
  • step: 40002

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: 32
  • 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
  • num_epochs: 10.0
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2