akreal

This field got reactivated recently, some new models were released (in the order of release, but the last one seems the best at the moment):

1. ZIPA https://github.com/lingjzhu/zipa

2. POWSM https://huggingface.co/espnet/powsm

3. PhoneticXEUS https://github.com/changelinglab/PhoneticXeus

I would be curious to know how to help people to use these models, or what kind of tasks they could be applied to.

AFAIK all ways of running docker on MacOS rely on a amd64 virtual machine with Linux kernel in it.

WhisperX is not a model but a software package built around Whisper and some other models, including diarization and alignment ones. Something similar will be built around the Cohere Transcribe model, maybe even just an integration to WhisperX itself.

I also expected screenshots there, especially given the word "interface". Turns out, it's not about user interface (UI), it's about programming interface (kinda API). It allows calling window-related functions on Macintosh, X Window System, and Atari. So the resulting windows were looking like a native UI, I assume.

Docling: https://github.com/docling-project/docling

There is a dolphin language model project from Google and Georgia Tech: https://blog.google/technology/ai/dolphingemma/

As far as I understand, the MMS TTS models are trained from scratch (section 7.1 of [1]), they do not employ any SSL models. So the OmniASR SSL models are not useful here.

What might be interesting is the newly released OmniASR data, because the MMS data, which was used for the MMS TTS, was never released.

Also, the OmniASR can be used to transcribe some untranscribed speech to train a TTS on it.

[1] MMS paper: https://arxiv.org/pdf/2305.13516

How is/was the data written to disks? Something like rsync/netcat?

Probably a mix-up with the recently released Huawei model:

https://news.ycombinator.com/item?id=44441447

What is the motivation to move startup from Canada to Germany, if I may ask?

I would be interested to see this reproducibility study.

Could this (or something similar) be found in public access/some libraries?

Telegram?

Doesn't moving air help evaporation anyhow?

The infrastructure problem should also have a relatively cheap technical solution. I assume the major bottleneck is bureaucracy, which largely has no technical workarounds so far.

It took the modern human brain quite a bit of observations to discover and formulate f=ma, it was originally published in 1687.

I was surprised to see this headline, because I had been using Plasma 5 on Intel graphics for almost a decade without any issues. After reading the article, it turns out that this is about Wayland, and I used X11. Wayland was indeed quite laggy when I tried it once, it's good to know it is solved now.

Cool!

HF Transformers is great for prototyping and research, but should not an interactive tool like this be based on something more speed-focused, like llama.cpp?

Any plans for languages beyond English?

Maybe this: "top designer Mark Krebs, who worked in Google's satellite and aircraft division"

https://www.reuters.com/article/us-spacex-starlink-insight-i...

Maybe you are referring to Stasi documents: https://www.stasi-unterlagen-archiv.de/en/archives/the-recon...

Edit: link to the English version.

I was curious about energy efficiency and took two samples from the linked MLPerf GPT3 results. H100 seems about three times more efficient than Gaudi2.

  256 Gaudi2 600W TDP: 256 * (442.578 / 60) * 0.6 = ~1133 kWh
  512 H100 700W TDP: 512 * (64.264 / 60) * 0.7 = ~384 kWh

Can't they install a normal Linux?

A shameless plug, my colleagues made a demo where you could create a virtually infinite amount of voices with some sort of control of how they sound like: https://huggingface.co/spaces/Flux9665/ThisSpeakerDoesNotExi...

Which prompt did you use for translation? I'd be curious to try it for my task too.

What else do you store besides movies and audio so that it becomes noticeble for you? I also use btrfs with zstd, but mainly see the difference for OS/apps files. Movies and audio don't compress as you noted, and code and scripts take tiny space anyway.

Not true for macOS.

One could outsource the work to other people.

There is also a comparison with CLD 2 in the repo of sister Python library:

https://github.com/pemistahl/lingua-py#4-how-good-is-it

CDL 2 seems to be slightly less accurate than CLD 3 on average.

Redirect it. Double Asteroid Redirection Test mission is going to test soon if this would work in practice:

https://en.m.wikipedia.org/wiki/Double_Asteroid_Redirection_...

> 118 degrees Fahrenheit (48 degrees Celsius)