firmware
whisper.cpp
firmware | whisper.cpp | |
---|---|---|
57 | 187 | |
2,761 | 31,426 | |
6.2% | - | |
9.9 | 9.8 | |
2 days ago | 1 day ago | |
C++ | C | |
GNU General Public License v3.0 only | 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.
firmware
- FireChat was a tool for revolution. Then it disappeared
-
Show HN: Extend Zigbee sensor range with LoRaWAN
This is a fantastic idea, thanks for sharing. I feel like LoRaWAN and LoRAMESH are the perfect solution for shuffling messaging around for home and property sensors, easily traversing a couple miles in poor conditions.
Prior to seeing this I was thinking about how to use the Meshtastic [0] project to fundamentally provide simple UDP services for message brokering over LoRa. There are so many sensors that could easily hook or connect to devices acting as network routers that could bridge other protocols across long distances very easily.
Have you looked at doing something similar with ZWave at all?
[0] https://meshtastic.org/
- Amateur Radio Fatalism
- Meshtastic: An open source, off-grid, decentralized, mesh network
-
T-Mobile introduce fines from Jan 1 for "Code of Conduct" violations
Truly independent peer-to-peer internet when?
Seriously, I think more and more about building a LoRa network with friends. https://meshtastic.org/
- What Is LoRa: The Fundamentals
-
FCC will vote on plan to remove outdated amateur radio technical restrictions
Agreed-- at least relaxing the restriction for UHF/SHF signals on a "secondary usage" basis (traffic must yield to plaintext). Potentially with with reduced power (say 100w) or minimum directionality, but I think a 'secondary usage' would be sufficient. Without doing so virtually all experimentation will continue to be deflected onto the ISM bands and we will lose our allocations through disuse.
So long as identification is still decodable, spectrum usage can be managed.
It's sufficient to prohibit commercial usage you don't need plaintext to do so. The old threat of tow trucks and cab services moving onto ham-bands had long since been mooted by ubiquitous cellular, but even if it weren't any significant commercial usage will eventually have a whistleblower. Usage that is obscure enough to not be vulnerable to whistleblowers could also be hidden just as well in "plaintext" traffic that was really uncrackable steganography.
As it stands you can't even lawfully log into your own personal systems over amateur radio even if you take the unreasonable steps of using specially modified software to authenticate-but-not-encrypt because inevitably some third party will send a message to you via the internet that contains some naughty words that aren't permitted over the radio.
Without relaxing the encryption rules, innovative radio usage like meshtastic (https://meshtastic.org/) will continue to be pushed onto ISM bands where (1) they're still technically unlawful because the homebrew hardware is not type-accepted (amateur bands are the ONLY place where homebrew intentional radiators are allowed!) and (2) where the band choices, power limit, and EIRP limits are detrimental to full exploration of the possibilities.
Besides, the FCC has long allowed proprietary, license fee bearing, patent encumbered digital modes. These are very close to encryption in terms of their ability to lock others out of ham comms, and have frequently been used by amateur radio groups to establish "lid free" communications channels. (Because most of the more irritating people aren't technically sophisticated enough to adopt some new mode without help, and people won't help them...).
The rules as they stand punish honest people who follow the intent and spirit of the rule in favor of people willing to just ignore the rules (including operating unlawful devices in ISM bands), willing to use stego, or willing to use obscure protocols to achieve the same ends that they'd otherwise achieve with encryption. It blocks modern networking by disallowing standard internet-grade software use with radio since all of it has integral encryption which generally can't be disabled to prevent downgrading and cross domain attacks in contexts where the encryption is needed -- or because in some cases the protocols are designed in such a way that authentication without encypherment isn't possible.
-
Qaul β Internet Independent Wireless Mesh Communication App
Meh.... very very low range.
For ~$20 you can get a LoRa dongle and https://meshtastic.org/, and with some luck (someone putting a node on a hgh building or a hill), you can reach quite impressive distances.
-
β³ 0 apps added, 10 updated at apt.izzysoft.de
Meshtastic (version 30109): An inexpensive open-source GPS mesh radio for hiking, skiing, flying, marching.
- Programadores Unite!
whisper.cpp
-
Show HN: I created automatic subtitling app to boost short videos
whisper.cpp [1] has a karaoke example that uses ffmpeg's drawtext filter to display rudimentary karaoke-like captions. It also supports diarisation. Perhaps it could be a starting point to create a better script that does what you need.
--
1: https://github.com/ggerganov/whisper.cpp/blob/master/README....
- LLaMA Now Goes Faster on CPUs
-
LLMs on your local Computer (Part 1)
The ggml library is one of the first library for local LLM interference. Itβs a pure C library that converts models to run on several devices, including desktops, laptops, and even mobile device - and therefore, it can also be considered as a tinkering tool, trying new optimizations, that will then be incorporated into other downstream projects. This tool is at the heart of several other projects, powering LLM interference on desktop or even mobile phones. Subprojects for running specific LLMs or LLM families exists, such as whisper.cpp.
-
Voxos.ai β An Open-Source Desktop Voice Assistant
I'm not sure if it is _fully_ openai compatible, but whispercpp has a server bundled that says it is "OAI-like": https://github.com/ggerganov/whisper.cpp/tree/master/example...
I don't have any direct experience with it... I've only played around with whisper locally, using scripts.
-
Jarvis: A Voice Virtual Assistant in Python (OpenAI, ElevenLabs, Deepgram)
unless i'm misunderstanding `whisper.cpp` seems to support streaming & the repository includes a native example[0] and a WASM example[1] with a demo site[2].
[0]: https://github.com/ggerganov/whisper.cpp/tree/master/example...
- Wchess
-
I've open sourced my Flutter plugin to run on-device LLMs on any platform. TestFlight builds available now.
Usage 1: Good to transcribe audio. An example use case could be to summarize YouTube videos or long courses. Usage 2: You talk with voice to your AI that responds with text (later with audio too). - https://github.com/ggerganov/whisper.cpp
-
Scrybble is the ReMarkable highlights to Obsidian exporter I have been looking for
π£οΈποΈ whisper.cpp (offline speech-to-text transcription, models trained by OpenAI, CLI based, browser based)
- Whisper.wasm
-
Whisper C++ not working for me. Anyone else?
Has anyone played around with Whisper C++ for swift? I'm hitting a snag even on the demo. I've downloaded the github repo and everything matches up with this video [ https://youtu.be/b10OHCDHDQ4 ] but when he hits the transcribe button, it actually prints out the captioning. When I do it, it skips that part and just says "Done...". But it, does everything else - plays the audio, says it's transcribing.. just doesn't show me the transcription: and it's not in the debug window either. But the demo isn't throwing any errors, and I haven't messed with the code really so this is their example. https://github.com/ggerganov/whisper.cpp
What are some alternatives?
disaster-radio - A (paused) work-in-progress long-range, low-bandwidth wireless disaster recovery mesh network powered by the sun.
faster-whisper - Faster Whisper transcription with CTranslate2
EBYTE - Libraries to program and use UART-based EBYTE wireless data transceivers
Whisper - High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
ESP32-Paxcounter - Wifi & BLE driven passenger flow metering with cheap ESP32 boards
bark - π Text-Prompted Generative Audio Model
LoRa-Stopwatch - Stopwatch with countdown for multiple devices being synchronized via LoRa
whisper - Robust Speech Recognition via Large-Scale Weak Supervision
ClusterDuck-Protocol - Firmware for an ad-hoc mesh network of Internet-of-Things devices based on LoRa (Long Range radio) that can be deployed quickly and at low cost.
whisperX - WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
ParaDrone - AutoPilot for Parachutes
llama.cpp - LLM inference in C/C++