MeloTTS

This section only explains how to run the precompiled MeloTTS text-to-speech demo on Raspberry Pi 5;
For model conversion and example source code compilation, please refer to melotts.axcl.

Download

git clone https://github.com/ml-inory/melotts.axcl.git
chmod +x build_aarch64.sh
./build_aarch64.sh

Precompiled Models

cd melotts.axcl
./download_models.sh

Precompiled model download links:

Compile

For aarch64 platform:

./build_aarch64.sh

Run MeloTTS

In the melotts.axcl project root directory, run:

./install/melotts -s sentence

Example for running with English model:

./install/melotts -e ../MeloTTS-English-ax650/encoder-en.onnx -d ../MeloTTS-English-ax650/decoder-en-au.axmodel -l ../MeloTTS-English-ax650/lexicon-en.txt -t ../MeloTTS-English-ax650/tokens-en.txt --g ../MeloTTS-English-ax650/g-en-au.bin -s "M5Stack is a leading provider of IoT solutions, committed to providing developers worldwide with convenient and flexible development components and tools."

Example Output:

m5stack@raspberrypi5:~/melotts.axcl $ ./install/melotts -e ../MeloTTS-English-ax650/encoder-en.onnx -d ../MeloTTS-English-ax650/decoder-en-au.axmodel -l ../MeloTTS-English-ax650/lexicon-en.txt -t ../MeloTTS-English-ax650/tokens-en.txt --g ../MeloTTS-English-ax650/g-en-au.bin -s "M5Stack is a leading provider of IoT solutions, committed to providing developers worldwide with convenient and flexible development components and tools."
encoder: ../MeloTTS-English-ax650/encoder-en.onnx
decoder: ../MeloTTS-English-ax650/decoder-en-au.axmodel
lexicon: ../MeloTTS-English-ax650/lexicon-en.txt
token: ../MeloTTS-English-ax650/tokens-en.txt
sentence: M5Stack is a leading provider of IoT solutions, committed to providing developers worldwide with convenient and flexible development components and tools.
wav: output.wav
speed: 0.800000
sample_rate: 44100
Load encoder
Load decoder model
Encoder run take 535.47ms
decoder slice num: 9
Decode slice(1/9) take 40.15ms
Decode slice(2/9) take 39.87ms
Decode slice(3/9) take 39.86ms
Decode slice(4/9) take 39.75ms
Decode slice(5/9) take 40.19ms
Decode slice(6/9) take 39.79ms
Decode slice(7/9) take 39.77ms
Decode slice(8/9) take 39.82ms
Decode slice(9/9) take 40.34ms
Saved audio to output.wav

Next Overview

Linux PC

CM4Stack

CoreMP135

AI Accelerator Card

LLM-8850 Card

Quick Start

Vision Models

Large Language Models

Multimodal Models

Audio Models

Generative Models

Advanced Usage

LLM

Real-Time AI Voice Assistant

OpenAI Voice Assistant

XiaoZhi Voice Assistant

XiaoLing Voice Assistant

AtomS3R-M12 Volcengine Kit

Offline Voice Recognition

Unit ASR

Home Assistant

Industrial Control

StamPLC

IoT Measuring Instruments

Air Quality

Module13.2 PPS

VAMeter

T-Lite

Ezdata

Ethernet Camera

PoECAM

Wi-Fi Camera

TimerCAM

Unit CamS3/-5MP

AI Camera

UnitV2

M5StickV/UnitV

LoRa & LoRaWAN

TTN (The Things Network)

Meshtastic

Motor Control

Unit Roller485/CAN

Develop Tools

Hobby Kit

Restore Factory Firmware