Whisper
endoflife.date
Whisper | endoflife.date | |
---|---|---|
32 | 43 | |
7,182 | 2,180 | |
- | 4.5% | |
6.5 | 9.9 | |
7 months ago | 7 days ago | |
C++ | Ruby | |
Mozilla Public License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Whisper
-
Nvidia Speech and Translation AI Models Set Records for Speed and Accuracy
I've been using WhisperDesktop ( https://github.com/Const-me/Whisper ) with great success on a 3090 for fast & accurate transcription of often poor quality euro-english hours long multispeaker audio files. If there's an easy way to compare I'm certainly going to give this a try.
-
AMD's CDNA 3 Compute Architecture
Why would you want OpenCL? Pretty sure D3D11 compute shaders gonna be adequate for a Torch backend, and they even work on Linux with Wine: https://github.com/Const-me/Whisper/issues/42 Native Vulkan compute shaders would be even better.
Why would you want unified address space? At least in my experience, it’s often too slow to be useful. DMA transfers (CopyResource in D3D11, copy command queue in D3D12, transfer queue in VK) are implemented by dedicated hardware inside GPUs, and are way more efficient.
-
Amazon Bedrock Is Now Generally Available
https://github.com/ggerganov/whisper.cpp
https://github.com/Const-me/Whisper
I had fun with both of these. They will both do realtime transcription. Bit you will have to download the training data sets…
-
Why Nvidia Keeps Winning: The Rise of an AI Giant
Gamers don’t care about FP64 performance, and it seems nVidia is using that for market segmentation. The FP64 performance for RTX 4090 is 1.142 TFlops, for RTX 3090 Ti 0.524 TFlops. AMD doesn’t do that, FP64 performance is consistently better there, and have been this way for quite a few years. For example, the figure for 3090 Ti (a $2000 card from 2022) is similar to Radeon RX Vega 56, a $400 card from 2017 which can do 0.518 TFlops.
And another thing: nVidia forbids usage of GeForce cards in data centers, while AMD allows that. I don’t know how specifically they define datacenter, whether it’s enforceable, or whether it’s tested in courts of various jurisdictions. I just don’t want to find out answers to these questions at the legal expenses of my employer. I believe they would prefer to not cut corners like that.
I think nVidia only beats AMD due to the ecosystem: for GPGPU that’s CUDA (and especially the included first-party libraries like BLAS, FFT, DNN and others), also due to the support in popular libraries like TensorFlow. However, it’s not that hard to ignore the ecosystem, and instead write some compute shaders in HLSL. Here’s a non-trivial open-source project unrelated to CAE, where I managed to do just that with decent results: https://github.com/Const-me/Whisper That software even works on Linux, probably due to Valve’s work on DXVK 2.0 (a compatibility layer which implements D3D11 on top of Vulkan).
-
Ask HN: What is your recommended speech to text/audio transcription tool?
Currently, I use a GUI for Whisper AI (https://github.com/Const-me/Whisper) to upload MP3s of interviews to get text transcripts. However, I'm hoping to find another tool that would recognize and split out the text per speaker.
Does such a thing exist?
- Da audio a testo, consigli?
-
Ask HN: Any recommendations for cheap, high-quality transcription software
I just used Whisper over the weekend to transcribe 5 hours of meeting, worked nicely and it can be run on a single GPU locally. https://github.com/ggerganov/whisper.cpp
There are a few wrappers available with GUI like https://github.com/Const-me/Whisper
- Voice recognition software for German
- Const-me/Whisper: High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
- I built a massive search engine to find video clips by spoken text
endoflife.date
-
End of Life of Technologies and Devices
> where you can see overlapped timelines when support ended
I tried to generate a visual timeline for a given page (https://github.com/endoflife-date/endoflife.date/pull/2859, has some screenshots), but it was limited to a single page (so you'd only see nokia devices at once for eg).
It turned out that it is too hard to generate clear charts with vague data. We often only know whether is device is supported or not (true/false, see comments about samsung below in this thread), and don't have clear release dates.
I'll get to it someday (PRs welcome), but it might not work for the usecase we want (picking phones) because data on mobiles is very vague.
repairability score -> sounds interesting, will file an issue and see. The hard part is that there's no clear identifiers for devices (SWID/CPE are just not good enough) for us to track this kind of data from elsewhere easily.
-
understanding Rails version maintenance policy?
Here's the PR where it was added by a user, "Based on a Rails core team member's comment"...
-
Pragmatic Versioning – An Alternative to Semver
A lot of the communications regarding End of Life for Support is done very effectively here: https://endoflife.date/
-
Maybe helpful: https://endoflife.date
https://endoflife.date (not mine)
-
Central Hardware Firmware versions?
a little similar to endoflife.date if anyone has ever come across it for Software versions?
-
You can serve static data over HTTP
We do this at https://endoflife.date API, and it works quite well.
-
python-eol: A package to check whether the python version you're using is beyond/close to end of life
I've created the `db.json` with the [end of life](https://endoflife.date/) api.
-
Ask HN: Most interesting tech you built for just yourself?
Something I've recently worked on is building an SQLite database of all the dependencies my organisation uses, which makes it possible to write our own queries and reports. The tool is all Open Source (https://dmd.tanna.dev) and has a CLI as well as the SQLite data.
Ive used it to look for software that's out of date (via https://endoflife.date), to find vulnerablilities (via https://osv.dev) and get license information (via https://deps.dev)
It's been hugely useful for us understanding use of internal and external dependencies, and I wish I'd built it earlier in my career so I could've had it for other companies I've worked at!
-
Keeping up with EOS and EOL hardware and software
This is neat: https://endoflife.date/
-
Looking for a 3rd party library of EOL/EOS software support dates
I'm looking for a 3rd party vendor that can do the mindlessly tedious work of maintaining a library of software support dates. Think hundreds of thousands/millions of versions of software in an enterprise with ridiculous tech debt. Something like endoflife.date but much more far encompassing.
What are some alternatives?
whisper.cpp - Port of OpenAI's Whisper model in C/C++
WordOps - Install and manage a high performance WordPress stack with a few keystrokes
whisper - Robust Speech Recognition via Large-Scale Weak Supervision
django-DefectDojo - DevSecOps, ASPM, Vulnerability Management. All on one platform.
TransformerEngine - A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.
xeol - A scanner for end-of-life (EOL) software and dependencies in container images, filesystems, and SBOMs
just-an-email - App to share files & texts between your devices without installing anything
radiofeed-app - Simple podcast aggregator
ggml - Tensor library for machine learning
public-iperf3-servers - A list of public iPerf3 servers...
beaker - An experimental peer-to-peer Web browser
digraph - Organize the world