Kedreamix/Linly-Talker

Issues

• 想问一下作者，这个可以用多卡进行推理吗

  #100 opened 2 months ago by kkkwjr
  2

• docker pull 之后应该怎么运行整个程序啊

  #116 opened 8 days ago by Crescentz
  0

• 使用webui的问题

  #115 opened 22 days ago by aa007shuai
  1

• 你好，在使用Musetalker的时候，报这个错误

  #88 opened 3 months ago by xuquankun
  2

• CosyVoice导入失败，

  #117 opened 21 days ago by Crescentz
  0

• 无法找到麦克风

  #94 opened 3 months ago by Rockycocky
  4

• 执行pip install -r requirements_webui.txt 遇到 ERROR: No matching distribution found for scikit_learn==1.4.2

  #114 opened 24 days ago by xy3xy3
  0

• docker拉取镜像启动报错及访问问题

  #112 opened a month ago by turndown
  1

• CG客户端运行webui.py报错

  #107 opened 2 months ago by Heaverno
  3

• 分离多个说话人 失败，不知道为啥出来就是一个人

  #113 opened a month ago by nishengdu
  1

• autodl镜像待更新

  #111 opened a month ago by xy3xy3
  0

• 啥时候能实现实时的流式数字人呀！期待一下

  #110 opened a month ago by kkkwjr
  0

• TypeError: object of type 'NoneType' has no len()

  #109 opened a month ago by 545089467
  0

• 加载自己的GPT-SoVITS模型失败

  #108 opened 2 months ago by levin-go
  0

• 我发现 app_img.py 会身体动作，但是下单身就不兼容了~~

  #103 opened 2 months ago by gg22mm
  4

• 启用webui报错

  #106 opened 2 months ago by mirai-ro
  2

• 请问如果想让整个人物动起来而不是只是面部，是否有办法实现呢？谢谢！

  #104 opened 2 months ago by Xinyu-HD
  0

• 请问下，视频中的字幕是怎么合成的

  #101 opened 2 months ago by caiji2019-cai
  2

• 如何通过docker compose 启动镜像

  #91 opened 2 months ago by verigle
  2

• AttributeError: 'MuseTalk_RealTime' object has no attribute 'audio_processor'

  #95 opened 3 months ago by astra-zhao
  2

• 在webui界面操作后，后台报错pydantic.errors.PydanticSchemaGenerationErro

  #99 opened 2 months ago by WSXDM2024
  2

• 大佬是不是可以直接搞一个数字人开源项目？

  #96 opened 2 months ago by davidxiao
  1

• 下载完成后报checkpoints不存在，无法移动

  #98 opened 2 months ago by skywalker2017
  1

• 点击 “语音识别（语音对话后点击）” 报错 pydantic_core._pydantic_core.ValidationError: 1 validation error for LogMessage

  #102 opened 2 months ago by gg22mm
  1

• 1

  #97 opened 3 months ago by zvxme
  0

• 请问一下，速度怎么样，会很慢吗？相对于每个原始的项目，速度怎么样？

  #77 opened 3 months ago by hjj-lmx
  1

• 如果采用实时流式对话模式，对硬件环境有什么具体要求？

  #89 opened 3 months ago by JerryDaHeLian
  1

• api的问题

  #74 opened 3 months ago by lxb0425
  4

• huggingface 模型文件有缺失，请更新一下最新的模型文件

  #92 opened 3 months ago by verigle
  4

• [W] [service.go:132] login to server failed: EOF报错，有大佬知道怎么解决吗

  #93 opened 3 months ago by kkkwjr
  3

• 请问 wav2lipv2.pth、yolov8n-face.pt 等模型文件有吗，哪里可以下载？

  #86 opened 3 months ago by lemwang
  4

• webui中的问题

  #90 opened 3 months ago by MikeAiJF
  1

• MuseTalk

  #78 opened 3 months ago by lxb0425
  1

• 性能很差 有什么办法吗

  #79 opened 3 months ago by lxb0425
  3

• 画面质量下降

  #80 opened 3 months ago by caterzy
  1

• 安装到pip install -r TFG/requirements_nerf.txt报错，按照方法解决不了

  #81 opened 3 months ago by hjj-lmx
  4

• 感谢分享，请问你这项目支持开源免费商用吗？

  #87 opened 3 months ago by JerryDaHeLian
  1

• python webui后，控制台显示

  #82 opened 3 months ago by hjj-lmx
  1

• 并发问题

  #83 opened 3 months ago by lgx1103
  1

• docker pull registry.cn-beijing.aliyuncs.com/codewithgpu2/kedreamix-linly-talker:zYGdW3yO3D出现下面错误，是正常现象吗？

  #84 opened 3 months ago by hjj-lmx
  1

• source_image要求

  #85 opened 3 months ago by lgx1103
  1

• 大佬，要不要考虑兼容一下阿里的CosyVoice，感觉他的效果比GPT-SoVITS要好

  #68 opened 4 months ago by miaojun22
  3

• 现在是否已经添加了对视频字幕的实现？

  #76 opened 4 months ago by chentiejin1
  2

• museV功能

  #71 opened 4 months ago by yanglibo0512
  1

• gr.Audio的音频时常问题

  #75 opened 4 months ago by maxchiron
  2

• 长文本下数字人视频中间无语音 说话跳词

  #72 opened 4 months ago by SanBingYouYong
  1

• 大佬要不建个微信交流群

  #67 opened 4 months ago by TnoobT
  3

• AutoDL加载自训练GPT-SoVITS模型报错

  #66 opened 4 months ago by klx1204
  1

• Musetalk不显示（小白求教）

  #70 opened 4 months ago by do-one-thing-to-well
  4

• 用docker拉取下来启动问题

  #69 opened 4 months ago by we1chao
  1