AI/EXPLORER
ToolsCategoriesSitesLLMsCompareAI QuizAlternativesPremium
—AI Tools
—Sites & Blogs
—LLMs & Models
—Categories
AI Explorer

Find and compare the best artificial intelligence tools for your projects.

Made within France

Explore

  • ›All tools
  • ›Sites & Blogs
  • ›LLMs & Models
  • ›Compare
  • ›Chatbots
  • ›AI Images
  • ›Code & Dev

Company

  • ›Premium
  • ›About
  • ›Contact
  • ›Blog

Legal

  • ›Legal notice
  • ›Privacy
  • ›Terms

© 2026 AI Explorer·All rights reserved.

HomeLLMsdgo tts training data speecht5 a

dgo tts training data speecht5 a

by sil-ai

Open source · 212 downloads · 0 likes

0.0
(0 reviews)AudioAPI & Local
About

This model is a refined version of *microsoft/speecht5_tts*, specifically trained for text-to-speech synthesis. It converts text into natural and expressive speech, with vocal quality optimized for various applications. Its primary use cases include generating voiceovers, providing voice assistance for visually impaired individuals, or creating automated audio content. What sets it apart is its ability to produce more natural intonation and prosody through targeted training, while maintaining the robustness of the base SpeechT5 model.

Documentation

dgo-tts-training-data-speecht5-a

This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0521

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: 8
  • eval_batch_size: 8
  • seed: 3407
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 4000
  • training_steps: 40000
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation Loss
0.08646.495910000.0616
0.072312.991820000.0563
0.065519.482930000.0578
0.06625.978840000.0527
0.060632.469850000.0539
0.057838.965760000.0519
0.056645.456870000.0531
0.057951.952780000.0534
0.051958.443790000.0521
0.051464.9396100000.0544
0.049771.4307110000.0578
0.048477.9266120000.0524
0.047484.4176130000.0526
0.045790.9135140000.0517
0.046197.4046150000.0523
0.0456103.9005160000.0530
0.0436110.3915170000.0517
0.042116.8874180000.0515
0.0411123.3785190000.0520
0.043129.8744200000.0514
0.0384136.3654210000.0529
0.0383142.8613220000.0516
0.0383149.3524230000.0518
0.0395155.8483240000.0520
0.038162.3393250000.0522
0.0383168.8352260000.0520
0.0363175.3263270000.0520
0.0378181.8222280000.0529
0.0373188.3132290000.0517
0.0364194.8091300000.0515
0.0362201.3002310000.0522
0.0365207.7961320000.0520
0.0339214.2871330000.0520
0.035220.7830340000.0514
0.0358227.2741350000.0522
0.0333233.7700360000.0525
0.0348240.2610370000.0524
0.0372246.7569380000.0519
0.0349253.2480390000.0521
0.0372259.7439400000.0521

Framework versions

  • Transformers 4.57.1
  • Pytorch 2.8.0+cu128
  • Datasets 4.2.0
  • Tokenizers 0.22.1
Capabilities & Tags
transformerssafetensorsspeecht5text-to-audiogenerated_from_trainerendpoints_compatible
Links & Resources
Specifications
CategoryAudio
AccessAPI & Local
LicenseOpen Source
PricingOpen Source
Rating
0.0

Try dgo tts training data speecht5 a

Access the model directly