flashlight
edgedict
Our great sponsors
flashlight | edgedict | |
---|---|---|
16 | 1 | |
5,145 | 281 | |
1.1% | - | |
7.7 | 0.0 | |
23 days ago | over 2 years ago | |
C++ | Python | |
MIT License | 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.
flashlight
-
MatX: Efficient C++17 GPU numerical computing library with Python-like syntax
I think a comparison to PyTorch, TensorFlow and/or JAX is more relevant than a comparison to CuPy/NumPy.
And then maybe also a comparison to Flashlight (https://github.com/flashlight/flashlight) or other C/C++ based ML/computing libraries?
Also, there is no mention of it, so I suppose this does not support automatic differentiation?
-
Project Resources
This Facebook ai project seems reasonably structured after looking at its CMakeLists.txt. CMake is a build generator for c++, it's how you make binaries to run your project: https://github.com/flashlight/flashlight
-
Meta AI Open Sources Flashlight: Fast and Flexible Machine Learning Toolkit in C++
Continue reading | Check out the paper and github link
- Flashlight: A C++ standalone library for machine learning
-
[D] Deep Learning Framework for C++.
I built and maintain Flashlight, a C++-first library for ML/DL. We built Flashlight to be:
- [R] C++ for Machine Learning
-
What is the most used library for AI in C++ ?
I’ve never used it, but Facebook’s flashlight looks interesting
-
Python.
Flashlight bro, not flash. Read again
-
Mozilla Common Voice Adds 16 New Languages and 4,600 New Hours of Speech
I've had good results with https://github.com/flashlight/flashlight/blob/master/flashli.... Seems to work well with spoken english in a variety of accents. Biggest limitation is that the architecture they have pretrained models for doesn't really work well with clips longer than ~15 seconds, so you have to segment your input files.
- [D] C++ in Machine Learning.
edgedict
-
Mozilla Common Voice Adds 16 New Languages and 4,600 New Hours of Speech
I created edgedict[0] a year ago part of my side projects. At that time this is the only open source STT with streaming capabilities. If anyone is interested the pretrained weights for english and chinese is available.
[0] https://github.com/theblackcat102/edgedict
What are some alternatives?
TTS - 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
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.
allosaurus - Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
PaddleSpeech - Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
STT - 🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.
vakyansh-models - Open source speech to text models for Indic Languages
NeMo - A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
DNS-Challenge - This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.