WeTTS model resources

将中文合成为语音，使用完整的多音字、韵律前端和 VITS 声学模型。

Board builds that Agora runs and measures on real Qualcomm boards. Try it online, without a board: https://mega.aidlux.com/models/wetts

SoC · board	Precisions	Measured on Agora (default precision)
QCS8550 · 犀牛派 X1 (Rhino Pi X1)	FP32	RTF 0.060
QCS6490 · 犀牛派 A1 (Rhino Pi A1)	FP32	RTF 0.101

Task: 语音合成. Inputs: text (text). Outputs: audio (audio).

Download

export AGORA_WORKSPACE="$HOME/my-wetts"
export AGORA_SOC='QCS8550'
hf download APLUX-Agora/WeTTS \
  --include "targets/$AGORA_SOC/*" --local-dir "$AGORA_WORKSPACE/resources"

Each targets/<SoC>/ holds model.json (default precision and variant paths) and one directory per precision. Context binaries are named model.bin; multi-file packages are kept as published by Model Farm.

Pre- and post-processing, the runner and an exported project: open the model on Agora and choose “部署指南”, or export any workflow that uses it.

Licence and provenance

Source model licence: see the original model's terms. Converted, deployable resources: APLUX Model Farm License (LICENSE_MODEL_FARM.pdf). See NOTICE.md and SHA256SUMS.