Revisiting Voice Cloning with GPT-SoVITS and so on

Forewords My last article on voice cloning is more than a year ago, and here we are again for adopting some latest advancement. Refering to some Chinese source such as this blog and this video, I was attempting to adopt new tools for my audio book service, such as CosyVoice, F5-TTS, GPT-SoVITS, and fish-speech. But before we start, I recommend to: Install miniconda for dependency sanity wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh && sudo chmod +x Miniconda3-latest-Linux-x86_64.sh && bash Miniconda3-latest-Linux-x86_64.sh Setup PyTorch environment as needed and confirm with python -m torch.utils.collect_env ...

June 11, 2025 · 8 min · Jun

Migrating Harbor instance from Linux to WSL2

In the past, I have covered how to set up Ubuntu in WSL2 and hosting local LLMs with Harbor, now I want to migrate my Harbor instance from baremetal Linux into WSL2 so that I don’t have to set it up from scratch. First thing to do is to open firewall port netsh interface portproxy add v4tov4 listenport=33811 listenaddress=0.0.0.0 connectport=33801 connectaddress=172.xx.xxx.xxx On Linux hardware: copy Harbor files from /home/username/Harbor /home/username/.ollama On Windows hardware: connect the USB drive containing Harbor files and run ...

May 26, 2025 · 1 min · Jun

Migrating Linux VM to a Portable Live USB

Last time, I mentioned Creating Ventoy VDI for Linux Live USB , however, it may not boot on some strange hardware and I unfortunately have quite a few of those. So in such cases, it’s better to boot Linux natively. By doing this, we need Rescuezilla/Clonezilla to extract the Linux system out of Virtualbox’s hard drive (VDI/VMDK). Download and load the ISO of Rescuezilla, a GUI version of Clonezilla, it’s larger but eaiser to use. ...

March 19, 2025 · 2 min · Jun

Self-hosting Local LLMs (DeepSeek-R1) Easily with Harbor (Ollama+Open-WebUI+SearXNG)

Lately, there is a need of private chatbot service as a complete alternative to OpenAI’s ChatGPT. So, I decide to implement one at home and make it accessible to everyone in my household alongside with my network printer and NAS (OpenMediaVault). In the past, I used to recommend people using Llama series for English tasks and Qwen series for Chinese tasks. There was no open-source model that’s strong enough in multilingual tasks comparing to proprietary ones (GPT/Claude). ...

January 26, 2025 · 5 min · Jun

Reviving ThinkCentre M58p in 2024

Days before mini-PC become a thing, there was no NUC, MinisForum or Beelink. It was the time of thin client and SFF (small-form-factor), manufacturers such as Shuttle, Dell and Lenovo were made a lot of these. Back then, the performance of SoC was too weak so that even laptops wouldn’t use them. But my first dedicated home lab machine was an Atom D525, which was called embedded industrial computer. It served as a router rather than server due to its performance and heat. That was also the time when I got into the world of m0n0wall derivatives (pfSense/FreeNAS). ...

December 14, 2024 · 3 min · Jun