metadata
license: other
language:
- ja
piper-plus-moe
Japanese Multi-Speaker Text-to-Speech Model based on VITS architecture, compatible with Piper TTS.
Model Overview
| Item | Value |
|---|---|
| Language | Japanese (ja) |
| Phoneme Type | OpenJTalk |
| Number of Speakers | 20 |
| Sample Rate | 22050 Hz |
| Training Epochs | 200 |
| Architecture | VITS |
| Framework | piper-plus |
Usage
With Piper TTS
# Download model files
wget https://huggingface.co/ayousanz/piper-plus-moe/resolve/main/moe-speech-20speakers-200epochs.onnx
wget https://huggingface.co/ayousanz/piper-plus-moe/resolve/main/moe-speech-20speakers-200epochs.onnx.json
# Run inference with Piper
echo "こんにちは、私は日本語音声合成モデルです。" | piper \
--model moe-speech-20speakers-200epochs.onnx \
--output_file output.wav \
--speaker 0
Training Command
NCCL_DEBUG=INFO NCCL_P2P_DISABLE=1 NCCL_IB_DISABLE=1 uv run python -m piper_train \
--dataset-dir /data/piper/dataset-moe-speech-20speakers \
--accelerator gpu --devices 4 --precision 16-mixed \
--max_epochs 200 --batch-size 32 --samples-per-speaker 4 \
--checkpoint-epochs 1 --quality medium \
--base_lr 2e-4 --disable_auto_lr_scaling \
--ema-decay 0.9995 --num-workers 0 --no-pin-memory \
--default_root_dir /data/piper/output-moe-speech-20speakers-lr2e4-fixed
Dataset
- Source: moe-speech dataset
- Total Speakers: 20
- Total Utterances: ~60,000
- Total Duration: ~90 hours
- Phoneme Type: OpenJTalk
Citation
@misc{piper-plus-moe,
author = {ayousanz},
title = {piper-plus-moe: Japanese Multi-Speaker TTS Model},
year = {2025},
publisher = {HuggingFace},
url = {https://huggingface.co/ayousanz/piper-plus-moe}
}