制作数字人

图像

Heygem：https://github.com/duixcom/Duix.Heygem

通过官方 readme 安装服务端

客户端

1. 通过 npm 构建
2. github 的发布

问题

TypeError: SQLite3 can only bind numbers, strings, bigints, buffers, and null

修改src\main\dao\f2f-model.js

const voiceIdInt = typeof voiceId === "boolean" ? (voiceId ? 1 : 0) : voiceId;
stmt.run(modelName, videoPath, audioPath, voiceIdInt, Date.now());

也有可能是视频问题

音频

index-tts：https://github.com/index-tts/index-tts

利用 docker compose 快速构建

1. 拉取源码

   git clone git@github.com:index-tts/index-tts.git

2. 进入文件夹

   cd index-tts

3. 下载模型

   模型地址：https://huggingface.co/IndexTeam/IndexTTS-1.5

   wget https://huggingface.co/IndexTeam/IndexTTS-1.5/resolve/main/bigvgan_discriminator.pth -P checkpoints
   wget https://huggingface.co/IndexTeam/IndexTTS-1.5/resolve/main/bigvgan_generator.pth -P checkpoints
   wget https://huggingface.co/IndexTeam/IndexTTS-1.5/resolve/main/bpe.model -P checkpoints
   wget https://huggingface.co/IndexTeam/IndexTTS-1.5/resolve/main/dvae.pth -P checkpoints
   wget https://huggingface.co/IndexTeam/IndexTTS-1.5/resolve/main/gpt.pth -P checkpoints
   wget https://huggingface.co/IndexTeam/IndexTTS-1.5/resolve/main/unigram_12000.vocab -P checkpoints
   wget https://huggingface.co/IndexTeam/IndexTTS-1.5/resolve/main/config.yaml -P checkpoints

4. 创建 docker 构建文件Dockerfile

   FROM continuumio/miniconda3
   
    # 创建 conda 环境并安装依赖
    RUN conda create -n index-tts python=3.10 -y && \
        echo "conda activate index-tts" >> ~/.bashrc
   
    SHELL ["/bin/bash", "-c"]
    ENV PATH /opt/conda/envs/index-tts/bin:$PATH
   
    # 安装 ffmpeg 和必要依赖
    RUN conda install -n index-tts -c conda-forge ffmpeg pynini==2.1.6 -y && \
        pip install torch torchaudio --index-url https://download.pytorch.org/whl/cu118
   
    # 设置工作目录（必须与 docker-compose 中一致）
    WORKDIR /app
   

5. 创建 docker 启动文件docker-compose.yml

   version: "3.8"
   
   services:
   indextts:
     build:
     context: .
     ports:
       - "7860:7860"
     volumes:
       - ./:/app/
     working_dir: /app
     command: ["python", "webui.py"]

6. 启动

   docker compose up -d