WeTTS
Text to Speech
FP32
post
WeTTS: Text To Speech

WETTS (WeNet End-to-End Text-to-Speech) is an open-source project based on WeNet, designed for end-to-end text-to-speech (TTS) conversion. The project aims to provide an efficient, flexible, and easy-to-use TTS system that supports multiple languages and voice styles. WETTS leverages advanced deep learning technologies, such as Transformer and WaveRNN, to achieve high-quality speech synthesis.

Source model

  • Input shape: Dynamic input
  • Number of parameters: --,--
  • Model size: 410M,65.9M
  • Output shape: Dynamic output

Source model repository: wetts

Performance Reference
Device
Backend
Precision
Inference Time
Accuracy Loss
File Size
Model Resource Acquisition

Model Farm provides optimized model resources and test code, which can be obtained through the following two methods:

  • Obtain via Model Farm page: Click Models & Test Code in the Performance Reference section on the right to obtain model resources and code packages.

  • Obtain via command line (Recommand): Users with APLUX development boards can obtain model resources and code packages through the built-in MMS tool.

# Search Models
mms list [model name]

# Get Models
mms get -m [model name] -p [precision] -c [soc] -b [backend] -d [file path]

For MMS usage, please refer to: MMS Usage & Access to Preview Models

Model Optimization

AIMO does not currently support automatic conversion of this model

Model Inference

SDK installation

pip install onnxruntime

Inference example

  • Click Model & Test Code to download model files and inference codes. The file structure showed below:
/model_farm_{model_name}_aidlite
    
    |__ models # folder where model files are stored

    |__ python # model inference example

    |__ cpp # model inference example

    |__ README.md
License
Source Model:APACHE-2.0
Deployable Model:APLUX-MODEL-FARM-LICENSE
Performance Reference
Device
Backend
Precision
Inference Time
Accuracy Loss
File Size