CensorCraft 是一款基于 Forge 的 Minecraft 模组,它通过 Simple Voice Chat 监听你的语音,并对说出违禁词的行为进行惩罚。
设置
若要测试该功能,请进入单人世界并对着麦克风说 "boom"(确保已启用 Simple Voice Chat 且麦克风未静音)。
如需更改惩罚方式,请打开 your_world/serverconfig/censorcraft-server.toml。详情请参阅 wiki 或相关视频!
工作原理
当你首次尝试加入一个世界时,系统会要求你下载一个 模型。随后在游戏中,你的音频流将使用该模型进行转录。如果检测到你说出了违禁词,可能会触发各种惩罚措施,例如:
- 使玩家爆炸
- 用闪电击中玩家
- 召唤任意生物给玩家
- 给予玩家任意药水效果
- 将玩家传送至随机维度
- 立即杀死玩家
- 执行任意命令
- ……或者借助 CensorCraft 插件实现的任何其他操作。
惩罚内容由服务器管理员设定,可在服务器配置文件中自定义。
常见问题
Q: 当我首次尝试加入世界时,提示需要下载“模型”。这是什么?
A: 模型是 CensorCraft 用于语音转录的工具。由于模型体积过大,无法直接打包进模组中,因此 CensorCraft 会在运行时将其下载到客户端的配置文件夹中。所有模型均由 HuggingFace 社区安全托管。
Q: 我得到了奇怪的转录结果。这是怎么回事?
A: 转录准确性取决于所使用的模型。虽然服务器管理员可以通过使用更大、更优质的模型来提高转录准确率,但转录并不总是完美的。如果你遇到了特别异常的结果,请从客户端配置文件夹中删除该模型,然后重新加入世界以再次安装模型。如果问题仍然存在,请在 GitHub 仓库中提交 Issue。
Q: 为什么运行速度这么慢?
A: 如果转录耗时过长,你可能会看到 “CensorCraft is far behind” 的提示。这通常由以下两个因素之一导致:要么你没有使用 GPU 进行转录,要么你的电脑性能不足以运行此模组。
如果检测到 Vulkan,转录将由 GPU 处理以提高速度。否则,系统将默认使用 CPU(通常速度较慢)。请确保已安装 Vulkan 并更新显卡驱动程序!
你可以在客户端配置中禁用 Use GPU 以改用 CPU(如果这样更快),或者调整客户端配置菜单中的 Latency 滑块以获得最佳效果。
CensorCraft is a Forge Minecraft mod that listens to your voice with Simple Voice Chat and punishes you for saying forbidden words.
Setup
To test it, hop into a single-player world and say "boom" into your microphone (with Simple Voice Chat enabled and your microphone unmuted).
To change punishments, open your_world/serverconfig/censorcraft-server.toml. See the wiki or video for details!
How it works
When you first try to join a world, you'll be asked to download a model. Then when in-game, your audio feed is transcribed using this model. If it detects you spoke a forbidden word, all sorts of punishment may be incurred, such as:
- Exploding the player
- Striking the player with lightning
- Summoning any mob by the player
- Giving the player any potion effect
- Teleporting the player to a random dimension
- Instantly killing the player
- Running any command
- … literally anything else with CensorCraft plugins.
Punishments are set by the server admin, configurable in the server config file.
Q/A
Q: When I first try to join a world, I'm asked to download a "model". What is it?
A: Models are what CensorCraft uses to transcribe your voice. Because models are too large to be bundled with the mod, CensorCraft downloads the model at runtime to your client config folder. All models are hosted safely by the HuggingFace community.
Q: I'm getting weird transcription results. What's happening?
A: Transcription accuracy is bound to the model. Although the server admin can increase transcription accuracy with a bigger and better model, transcription isn't always perfect. If you are getting particularly unusual results, delete the model from your client config folder and rejoin the world to install the model again. If it persists, open an issue in the GitHub repo.
Q: Why is it so slow?
A: You may see a "CensorCraft is far behind" message if transcription is taking too long. This caused by one of two factors: either you're not using the GPU for transcription, or your machine isn't powerful enough to run this mod.
If Vulkan is found, transcription is handled by your GPU to increase transcription speed. If not, it'll default to using the CPU (which is almost always slower). Make sure you have Vulkan installed and ensure your graphics drivers are up to date!
You can disable Use GPU in the client config to use your CPU if it's faster, or play with the Latency bar in your client config menu to get the best results.
评论 0
登录后参与评分
还没有评论,来抢沙发吧