Neat! While the physicality of having the CD spin while running inference is undeniably cool, I wonder if you could run larger models at higher speeds through the PS2 HDD accessory/Memory Card Micro SD adapter/the PS2's USB port.
I doubt the VUs can help with inference given their small scratchpad sizes and instruction set though, haha.
Heh, funny you mention that, considering Be's pivot to BeIA. Some Be engineers also worked on the (unreleased) Palm OS Cobalt, and eventually, Android. (And then Fuschia, but I don't think that OS will ever hit smartphones.)
Haiku does support WLAN adapters (even USB ones), through the support isn't as extensive as Linux or the BSDs. You might want to use the current nightly builds instead of the latest beta version, though, which was released in December 2022.
Does this do RAG over the character's chat history too? That's something SillyTavern can also do with extensions, but I figured since your project already uses Llamaindex, this feature can be something that's already baked in from the get-go.
I played with it some more and I have to agree. For actual voice _cloning_, XTTS2 sounds much, much closer to the original speaker. But the resulting output is also much more unpredictable and sometimes downright glitchy compared to OpenVoice. XTTS2 also tries to "act out" the implied emotion/tone/pitch/cadence in the input text, for better or worse.
But my use case is just to have a nice-sounding local TTS engine, and current text-to-phoneme conversion quirks aside, OpenVoice seems promising. It's fast, too.
This is HN, so I'm surprised that no one in the comments section has run this locally. :)
Following the instructions in their repo (and moving the checkpoints/ and resources/ folder into the "nested" openvoice subfolder), I managed to get the Gradio demo running. Simple enough.
It appears to be quicker than XTTS2 on my machine (RTX 3090), and utilizes approximately 1.5GB of VRAM. The Gradio demo is limited to 200 characters, perhaps for resource usage concerns, but it seems to run at around 8x realtime (8 seconds of speech for about 1 second of processing time.)
EDIT: patched the Gradio demo for longer text; it's way faster than that. One minute of speech only took ~4 seconds to render. Default voice sample, reading this very comment: https://voca.ro/18JIHDs4vI1v
I had to write out acronyms -- XTTS2 to "ex tee tee ess two", for example.
The voice clarity is better than XTTS2, too, but the speech can sound a bit stilted and, well, robotic/TTS-esque compared to it. The cloning consistency is definitely a step above XTTS2 in my experience -- XTTS2 would sometimes have random pitch shifts or plosives/babble in the middle of speech.
I found this recent thread interesting, specifically about really considering whether you're going to read the data you just wrote in the near future or not (in which case, use direct IO) and a set of (abandoned?) patches for write-behind caching for sequential writes in Linux (https://lore.kernel.org/lkml/156896493723.4334.1334048120714...).
The unlock tool would only work if it successfully authenticates with Xiaomi's server with matching Mi Cloud ID as the one previously registered to the device. So I very much doubt that it is stolen.
Glad to see that noise reduction is on the roadmap! Does Filmulator support embedded lens profiles? I enjoyed using Filmulator btw, its default output are just lovely.
If the equalization is done near the end of the audio output chain (ex: music player, defaults at 100% volume -> user sets master audio output volume to 50% -> EQ is applied) then a pre-amp is not strictly necessary if the EQ can take advantage of the extra headroom in the output channel. Otherwise, an adjustable pre-amp / gain setting would be nice, preferable with the option for it to automatically set itself to reduce by the maximum gain the EQ is applying to avoid clipping. But yeah, it should be optional; if the user wants stuff to clip, let it clip.
Switching to another virtual desktop (Win+Tab) can help if the graphics driver is still working normally. If the driver crashed, you have to wait for TDR to kick in and restart the driver (usually ~5s). That is, if it's able to recover.
The G203 has onboard memory (which also includes RGB light state / startup effect and DPI steps), so once you have your settings right you can just store the profile in the mouse and uninstall the software.
The latest version of the Logitech software (G HUB) doesn't make this feature obvious though, you have to set a local profile then click the gear icon > my gear > click the mouse image > switch on on-board memory mode > click Slot 1 (Default) > click replace with [the profile you just customized, usually Desktop (default.)
The old Logitech Gaming Software was much simpler in this regard.
As weird as it sounds, it might be related to your system region settings, specifically the decimal point sign and the thousands separator sign. I've been only able to open CSVs by manually importing them with Excel's 'import data from text file' function.
I doubt the VUs can help with inference given their small scratchpad sizes and instruction set though, haha.