AXERA-TECH / ZipVoice.AXERA

ZipVoice.AXERA

ZipVoice 板端推理 demo。

功能

• 支持中文和英文语音生成。
• 支持语音克隆。

模型转换

模型量化参考:

• Pulsar2 Docs — How to Convert ONNX to axmodel
• export / quantization Project

支持平台

• AX650
  • M4N-Dock（爱芯派Pro）
  • M.2 Accelerator Card

目录结构

ZipVoice.AXERA/
├── assets/
│   ├── moss_prompts/
│   └── paragraphs/
├── configs/
├── models/
│   └── axmodels/
├── resources/
│   ├── vocos-mel-24khz/
│   └── zipvoice_hf/
├── scripts/
├── infer_zipvoice_axera.py
├── requirements.txt
└── README.md

环境

安装 pyaxengine

pyaxengine Releases 下载对应版本的 .whl 文件，然后安装：

pip3 install axengine-x.x.x-py3-none-any.whl

Python 依赖

pip3 install -r requirements.txt

推理命令

进入目录：

cd ZipVoice.AXERA

句子

中文句子

合成文本：

今天午后天气很好，我打开窗户，听见远处有人聊天，水杯也轻轻晃了一下。

推理命令：

python3 infer_zipvoice_axera.py \
  --text "今天午后天气很好，我打开窗户，听见远处有人聊天，水杯也轻轻晃了一下。" \
  --prompt-text "不管怎么样我和汤姆还是要感谢贝尔卡金的援手" \
  --prompt-wav assets/moss_prompts/zh_1_4p5s.wav \
  --output-wav outputs/zh_sentence.wav \
  --num-step 10 \
  --seed 42

推理结果：

推理耗时: 5.781s
生成语音耗时: 6.411s
RTF: 0.9018

音频： outputs/zh_sentence.wav
提示音： assets/moss_prompts/zh_1_4p5s.wav

英文句子

合成文本：

This morning, a small train left the station, carrying sleepy passengers toward a bright coastal town.

推理命令：

python3 infer_zipvoice_axera.py \
  --text "This morning, a small train left the station, carrying sleepy passengers toward a bright coastal town." \
  --prompt-text "This is almost twice the current industry production level per train." \
  --prompt-wav assets/moss_prompts/en_4_4p5s.wav \
  --output-wav outputs/en_sentence.wav \
  --num-step 10 \
  --seed 42

推理结果：

推理耗时: 5.711s
生成语音耗时: 6.411s
RTF: 0.8909

音频： outputs/en_sentence.wav
提示音： assets/moss_prompts/en_4_4p5s.wav

段落

中文段落

合成文本：

窗外的银杏叶又黄了。我坐在老家的院子里，看那一片片扇形的叶子在风中轻轻摇摆，像是无数小扇子，扇走了夏天最后的暑气，也扇来了秋天的凉意。阳光透过枝叶的缝隙洒下来，在地上投下斑驳的光影，那光影随着风不停地晃动，像一群调皮的孩子在捉迷藏。说起来，这棵银杏树是我爷爷年轻时种下的，算算已有十多年了。爷爷去年秋天走了，走的时候，银杏叶正黄得灿烂。我记得他临终前说的最后一句话是：“叶子落了，来年还会再长。”当时我不太明白这句话的意思，现在看着满树金黄，忽然好像懂了些什么。

推理命令：

python3 infer_zipvoice_axera.py \
  --text-file assets/paragraphs/zh_ginkgo.txt \
  --prompt-text "不管怎么样我和汤姆还是要感谢贝尔卡金的援手" \
  --prompt-wav assets/moss_prompts/zh_1_4p5s.wav \
  --output-wav outputs/zh_long_paragraph.wav \
  --num-step 10 \
  --seed 42

推理结果：

推理耗时: 40.292s
生成语音耗时: 44.744s
RTF: 0.9005

音频： outputs/zh_long_paragraph.wav
提示音： assets/moss_prompts/zh_1_4p5s.wav

英文段落

合成文本：

At dusk, I saw an old scavenger digging through a bin on a quiet street corner. His clothes were torn, his back bent from years of labor. I was about to walk past him, as most people did, when something made me stop. From the pile of waste, he pulled out a thin, battered book. Curious, I stepped closer. It was a collection of poems, its pages yellowed and its cover stained. Instead of tossing it aside, the old man wiped the dirt off with his sleeve. Then, in a soft, trembling voice, he began to read: "Beside the eastern fence, I pick chrysanthemums; in quiet leisure, I see the southern hills." The words floated in the evening air. At that moment, the setting sun touched his silver hair, and his eyes, bright and clear, seemed to belong to someone else entirely. He was no longer a scavenger standing by garbage; he was a traveler in a world of beauty and peace. After a long while, he closed the book, pressed it gently to his chest, and slipped it inside his worn jacket. Then he went back to searching for plastic bottles, his movements slow and steady. I stood there, speechless.

推理命令：

python3 infer_zipvoice_axera.py \
  --text-file assets/paragraphs/en_scavenger.txt \
  --prompt-text "This is almost twice the current industry production level per train." \
  --prompt-wav assets/moss_prompts/en_4_4p5s.wav \
  --output-wav outputs/en_long_paragraph.wav \
  --num-step 10 \
  --seed 42

推理结果：

推理耗时: 62.161s
生成语音耗时: 64.749s
RTF: 0.9600

音频： outputs/en_long_paragraph.wav
提示音： assets/moss_prompts/en_4_4p5s.wav

参数说明

• --prompt-wav ：参考音频，用于控制音色，长度需控制在3-5s之内。
• --prompt-text ：参考音频对应文本，必须尽量和 prompt-wav 内容一致，否则 tokenizer 长度和音频帧数不匹配，会影响语速和效果。
• --num-step ：采样步数。步数越大通常效果更稳，推理耗时线性增加(当 num-step=8 时，以上推理的 rtf=0.75 左右)。
• --max-feat-len ：decoder 固定 feature 长度，当前为 1024。

参考

• ZipVoice