Kaldi Speech Recognition Toolkit
void-packages
Our great sponsors
Kaldi Speech Recognition Toolkit | void-packages | |
---|---|---|
22 | 671 | |
13,706 | 2,374 | |
1.2% | 2.9% | |
7.4 | 10.0 | |
3 months ago | 4 days ago | |
Shell | Shell | |
GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
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.
Kaldi Speech Recognition Toolkit
-
Amazon plans to charge for Alexa in June–unless internal conflict delays revamp
Yeah, whisper is the closest thing we have, but even it requires more processing power than is present in most of these edge devices in order to feel smooth. I've started a voice interface project on a Raspberry Pi 4, and it takes about 3 seconds to produce a result. That's impressive, but not fast enough for Alexa.
From what I gather a Pi 5 can do it in 1.5 seconds, which is closer, so I suspect it's only a matter of time before we do have fully local STT running directly on speakers.
> Probably anathema to the space, but if the devices leaned into the ~five tasks people use them for (timers, weather, todo list?) could probably tighten up the AI models to be more accurate and/or resource efficient.
Yes, this is the approach taken by a lot of streaming STT systems, like Kaldi [0]. Rather than use a fully capable model, you train a specialized one that knows what kinds of things people are likely to say to it.
[0] http://kaldi-asr.org/
- Unsupervised (Semi-Supervised) ASR/STT training recipes
-
Steve's Explanation of the Viterbi Algorithm
You can study CTC in isolation, ignoring all the HMM background. That is how CTC was also originally introduced, by mostly ignoring any of the existing HMM literature. So e.g. look at the original CTC paper. But I think the distill.pub article (https://distill.pub/2017/ctc/) is also good.
For studying HMMs, any speech recognition lecture should cover that. We teach that at RWTH Aachen University but I don't think there are public recordings. But probably you should find some other lectures online somewhere.
You also find a lot of tutorials for Kaldi: https://kaldi-asr.org/
Maybe check this book: https://www.microsoft.com/en-us/research/publication/automat...
The relation of CTC and HMM becomes intuitively clear once you get the concept of HMMs. Often in terms of speech recognition, it is all formulated as finite state automata (FSA) (or finite state transducer (FST), or weighted FST (WFST)), and the CTC FST just looks a bit different (simpler) than the traditional HMMs, but in all cases, you can think about having states with possible transitions.
This is all mostly about the modeling. The training is more different. For CTC, you often calculate the log prob of the full sequence over all possible alignments directly, while for HMMs, people often use a fixed alignment, and calculate framewise cross entropy.
I did some research on the relation of CTC training and HMM training: https://www-i6.informatik.rwth-aachen.de/publications/downlo...
-
[D] What's stopping you from working on speech and voice?
- https://github.com/kaldi-asr/kaldi
-
C++ for machine learning
Additionally, C++ may be used for extremely high levels of optimization even for cloud-based ML. Dlib and Kaldi are C++ libraries used as dependencies in Python codebases for computer vision and audio processing, for example. So if your application requires you to customize any functions similar to those libraries, then you'll need C++ knowhow.
-
The Advantages and disadvantages of In-House Speech Acknowledgment
Frameworks as well as toolkits like Kaldi were at first promoted by the research study area, yet nowadays used by both scientists and also market experts, reduced the access obstacle in the advancement of automatic speech recognition systems. Nonetheless, cutting edge methods need big speech data readies to achieve a usable system.
-
xbp-src to only cross compile 32-bit
Hello. I'm trying to package the openfst library (here)[https://github.com/void-linux/void-packages/pull/39015] but a developer says 32-bit must be cross compiled from 64-bit. I see xbps-src has a nocross option, but I don't see a way to only cross compile. What do you think I should do? I have currently limited the archs to 64-bit ones. Here's my issue with the developer's response: https://github.com/kaldi-asr/kaldi/issues/4808 Thank you.
-
Machine Learning with Unix Pipes
If you interested in unix-like software design and not yet familiar with kaldi toolkit, you definitely need to check it https://kaldi-asr.org
It extended Unix design with archives, control lists and matrices and enabled really flexible unix-like processing. For example, recognition of a dataset looks like this:
extract-wav scp:list.scp ark:- | compute-mfcc-feats ark:- ark:- | lattice-decoder-faster final.mdl HCLG.fst ark:- ark:- | lattice-rescore ark:- ark:'|gzip -c > lat.gzip'
Another example is gstreamer command line.
-
Lexicap: Lex Fridman Podcast Whisper Captions by Andrej Karpathy
No, speaker diarization is not part of Whisper. There are open source projects - such as Kaldi [1], but it's hard to get them running if you are not an area expert.
[1] https://kaldi-asr.org/
-
Is there a way to integrate a raspberry pi with a keyboard to do speech to text?
State-of-the-art ASR, like what you get on smartphones, has unfortunately high resource requirements. Some recent smartphone models are able to run ASR on-device, but more typically, ASR is done by sending audio to a web service. Check out the (currently experimental) Web SpeechRecognition API in a Chrome browser. Here is a demo of the API in action. For something open source, check out Kaldi ASR.
void-packages
-
Damn Small Linux 2024
I was looking for a lightweight OS to run on old Asus Eee PC 1005 HA, which uses a 32-bit Intel Atom N270 processor. I installed Void Linux (https://voidlinux.org/).
I may give DSL 2024 a try and see how it compares.
- Chimera Linux
-
When are we ditching systemd?
Linux Void
- Une nouvelle mise à jour de Systemd permettra à Linux de bénéficier de l'infâme "écran bleu de la mort" de Windows, mais la fonctionnalité a reçu un accueil très mitigé
-
How do I update one of these premade ESP32 boards?
My computer is running Void Linux and it has only a wired network connection. I can hook up my phone for USB tethering if I need to connect to the WiFi of the ESP32. How do I update the software without downloading some shady programs from filesharing site links on my system? I have the Arduino IDE and the esptool.py script installed.
- Linuxi kasutaja, mis distrot kodus kasutad ja millest see valik?
- I want to be a packager
-
Hyphens, minus, and dashes in Debian man pages
Classic "everyone is using the software wrong, but it's the fault of everyone, and not the software".
Some distros like Void seem to patch this out.[1]
From mandoc/mdocml's mandoc_char(7) [2]
In roff(7) documents, the minus sign is normally written as ‘\-’. In manual pages, some style guides recommend to also use ‘\-’ if an ASCII 0x2d “hyphen-minus” output glyph that can be copied and pasted is desired in output modes supporting it, for example in -T utf8 and -T html. But currently, no practically relevant manual page formatter requires that subtlety, so in manual pages, it is sufficient to write plain ‘-’ to represent hyphen, minus, and hyphen-minus.
Which is the common-sense thing to do.
Meanwhile, GNU projects become increasingly less relevant due to obnoxiousness like this.
In general the amount of wankery of "the correct hyphen" is staggering.
[1]: https://man.openbsd.org/mandoc_char
[2]: https://github.com/void-linux/void-packages/blob/20c66829134...
-
Thoughts on Void Linux?
So I was about to configure a new Archlinux build on my PC and came across Void Linux. I had already read about it a year ago but never researched it in depth. I know that is a Linux distribution made from scratch, with a different package manager and so on. Void Linux users or people who have tried it, what are your thoughts on it? Do you think the PM is easy to use? what about updates and bugs? what desktop or Tilling Window Manager do you use? could you tell me about it?
-
Question about python venv
Good news about dbus-next: https://github.com/void-linux/void-packages/pull/46760
What are some alternatives?
vosk-api - Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
AppImageLauncher - Helper application for Linux distributions serving as a kind of "entry point" for running and integrating AppImages
DeepSpeech - DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
ungoogled-chromium - Google Chromium, sans integration with Google
pyannote-audio - Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
gentoo - Official Gentoo ebuild repository
speech-and-text-unity-ios-android - Speed to text in Unity iOS use Native Speech Recognition
nix - Nix, the purely functional package manager
espnet - End-to-End Speech Processing Toolkit
sway - i3-compatible Wayland compositor
rhasspy - Offline private voice assistant for many human languages
xdeb - XDEB - Convert deb (Debian) packages to xbps (Void Linux)