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.

HomeLLMsspeecht5 ngiemboon

speecht5 ngiemboon

by mimba

Open source · 274 downloads · 0 likes

0.0
(0 reviews)AudioAPI & Local
About

The *speecht5-ngiemboon* model is a refined version of *microsoft/speecht5_tts*, specifically designed for speech synthesis. It converts text into natural-sounding speech, delivering a clear and expressive voice suitable for various contexts. Its primary use cases include generating automated audio content, assisting visually impaired individuals, and creating voices for virtual assistants. What sets it apart is its ability to produce intonation and fluidity that closely resemble human speech while remaining accessible through simple tools. Its training on specific datasets ensures optimized performance for natural language applications.

Documentation

speecht5-ngiemboon

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

  • Loss: 0.5604

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • 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: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 15
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation Loss
1.55790.72525000.7537
1.36041.449610000.6883
1.28142.174015000.6343
1.23082.899220000.6164
1.21333.623625000.6057
1.18294.348130000.5962
1.17875.072535000.5967
1.16925.797740000.5852
1.14726.522145000.5811
1.13747.246650000.5768
1.16437.971755000.5711
1.13858.696260000.5713
1.13349.420665000.5670
1.156410.145070000.5684
1.115810.870275000.5622
1.115811.594680000.5628
1.114912.319185000.5611
1.108813.043590000.5597
1.119113.768795000.5615
1.109714.4931100000.5604

Framework versions

  • Transformers 5.0.0
  • Pytorch 2.10.0+cu130
  • Datasets 2.18.0
  • Tokenizers 0.22.2
Capabilities & Tags
transformerstensorboardsafetensorsspeecht5text-to-audiogenerated_from_trainerendpoints_compatible
Links & Resources
Specifications
CategoryAudio
AccessAPI & Local
LicenseOpen Source
PricingOpen Source
Rating
0.0

Try speecht5 ngiemboon

Access the model directly