rust-bert
talk-to-chatgpt
rust-bert | talk-to-chatgpt | |
---|---|---|
7 | 19 | |
2,427 | 1,938 | |
- | - | |
6.8 | 7.5 | |
about 2 months ago | about 2 months ago | |
Rust | JavaScript | |
Apache License 2.0 | GNU Affero General Public License v3.0 |
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.
rust-bert
-
How to leverage the state-of-the-art NLP models in Rust
brew install libtorch brew link libtorch brew ls --verbose libtorch | grep dylib export LIBTORCH=$(brew --cellar pytorch)/$(brew info --json pytorch | jq -r '.[0].installed[0].version') export LD_LIBRARY_PATH=${LIBTORCH}/lib:$LD_LIBRARY_PATH git clone https://github.com/guillaume-be/rust-bert.git cd rust-bert ORT_STRATEGY=system cargo run --example sentence_embeddings
-
Transformers.js
I'd like to use this transformer model in rust (because it's on the backend, because I can use data munging and it will be faster, and for other reasons). It looks like a good model! But, it doesn't compile on Apple Silicon for wierd linking issues that aren't apparent - https://github.com/guillaume-be/rust-bert/issues/338. I've spent a large part of today and yesterday attempting to find out why. The only other library that I've found for doing this kind of thing programmatically (particularly sentiment analysis) is this (https://github.com/JohnSnowLabs/spark-nlp). Some of the models look a little older, which is OK, but it does mean that I'd have to do this in another language.
Does anyone know of any sentiment analysis software that can be tuned (other than VADER - I'm looking for more along the lines of a transformer model) - like BERT, but is pretrained and can be used in Rust or Python? Otherwise I'll probably using spark-nlp and having to spin another process.
Thanks.
-
Running large language models like ChatGPT on a single GPU
Give this a look: https://github.com/guillaume-be/rust-bert
If you have Pytorch configured correctly, this should "just work" for a lot of the smaller models. It won't be a 1:1 ChatGPT replacement, but you can build some pretty cool stuff with it.
> it's basically Python or bust in this space
More or less, but that doesn't have to be a bad thing. If you're on Apple Silicon, you have plenty of performance headroom to deploy Python code for this. I've gotten this library to work on systems with as little as 2gb of memory, so outside of ultra-low-end use cases, you should be fine.
-
Self-hosted Whisper-based voice recognition server for open Android phones
I suspect something similar is possible with ChatGPT. Using the GPT-neo-125m model I've been able to get some really convincing (if lackluster) answers on 4 core ARM hardware and less than 2gb of memory. With enough sampling, you can get legible paragraph-length responses out in less than 10 seconds; that's pretty good for an offline program in my book.
I'm using rust-bert to serve it over a Discord bot, similar to one of their examples[0]. It's running on Oracle VCPUs right now, but with dedi hardware and ML acceleration I can imagine the field moving really quickly.
[0] https://github.com/guillaume-be/rust-bert/blob/master/exampl...
-
Ask HN: What AI developer tools do you wish you'd discovered sooner?
Maybe a little played-out, but I've been having a blast with the rust-bert library this weekend: https://github.com/guillaume-be/rust-bert
With a little fanagling, you can get the GPT-Neo-1.3b model running on those free Oracle ARM VMs you can provision. I'm impressed, especially with the performance of the smallest model that uses less than a gig of memory.
-
Ask HN: Has anyone made a toy that integrates ChatGPT with voice into a toy?
Nope, but it's probably possible on a smaller, hobbyist scale. I've been playing with a few GPT libraries this week (namely rust-bert[0]) and I've been really impressive with local generation results on my crappy 2 core netbook. I can get 2 sentences to generate in ~5 seconds, which is pretty good in my book.
Armed with a Pi-style SBC and your AI library of choice, I bet you could get pretty far implementing some stuff. Bonus points if you use Whisper for speech-to-text, and double brownie points if you can get an AI voice to read the generation back.
[0] https://github.com/guillaume-be/rust-bert/tree/master/exampl...
-
[D] Is Rust stable/mature enough to be used for production ML? Is making Rust-based python wrappers a good choice for performance heavy uses and internal ML dependencies in 2021?
If you are using BERT models and some miscellaneous other related stuff then you should check out the rust-bert and Bert Sentence repos https://github.com/guillaume-be/rust-bert
talk-to-chatgpt
-
Now, ChatGPT can see my screen. Should I build this out? [video]
I'm trying to decide if it's worth cleaning up the code and publishing this. Is it something that would be interesting to others? It's still pretty buggy, in part because ChatGPT itself is buggy, particularly these past few days! But also, I have to regularly refresh the chrome tab when mic access or audio playback stops working. It's going to take some effort to make this thing more reliable. I need to better understand how the background page & service workers works with Chrome extensions.
This project started after I tried a bunch of Chrome plugins that let you speak to Chat GPT. The one I liked best was this one: https://github.com/C-Nedelcu/talk-to-chatgpt
I forked the code and refactored it quite a bit in order to improve the voice recognition, improve the quality of text-to-speech (using WellSaid) and then I added the screen capture capabilities. That's when it started feeling truly magical and useful to me.
The biggest issue is that ChatGPT is still too slow, but Sam Altman claimed during devday that improving the speed is the next biggest priority for them.
-
NEW: ChatGPT plugin store can be searched now!
That will be amazing for sure, but there is Talk-to-GPT in the meantime. The speechki plugin can also do limited text to speech.
-
WhisperChat: An Open Source, Voice Based conversational assistant using React/Node
Talk-To-ChatGPT is a popular one, and I believe it has API integration with ElevenLabs, so you can create custom voices. The repository is here and the extension is here. There are many more if you search the Chrome web store.
-
What's the most user friendly voice interface to GPT? Speech for both input and output, paid or providing your own API key is ok.
i like https://github.com/C-Nedelcu/talk-to-chatgpt a lot. you can use elevenlabs api key and use own custom voices.
-
Streamlining GPT Workflow
There's this: https://github.com/C-Nedelcu/talk-to-chatgpt
-
Is there a version of ChatGPT that you can speak to and have it speak back?
https://github.com/C-Nedelcu/talk-to-chatgpt (and the actual resultant extension: https://chrome.google.com/webstore/detail/talk-to-chatgpt/hodadfhfagpiemkeoliaelelfbboamlk)
- SUPER COOL!! Crosstalk with talk-to-chatgpt chrome extension powered AI partner.
-
I made a new ChatGPT interface!
I like it! Would be really nice if you could add text-to-speech, ideally both with cheap options (Azure/Google/Amazon) and something like elevenlabs. Like in https://github.com/1nnovat1on/gpt_chatbot and https://github.com/C-Nedelcu/talk-to-chatgpt
- Integrated voice recognition and text to speech
-
What are some ways that you make ChatGPT verbally conversational or otherwise more *naturally* conversational?
Today I discovered https://github.com/C-Nedelcu/talk-to-chatgpt, which is a great concept. Having a verbal conversation with ChatGPT is much more engaging for me. Do you have any special ways to simulate a more real conversation?
What are some alternatives?
Dlib - A toolkit for making real world machine learning and data analysis applications in C++
CopperAI - CopperAI offers a hands-free, voice-to-voice interaction system with a Large Language Model (LLM)
speak - Talk with your machine in this minimalistic Rust crate!
tortoise-tts - A multi-voice TTS system trained with an emphasis on quality
FlexGen - Running large language models like OPT-175B/GPT-3 on a single GPU. Focusing on high-throughput generation. [Moved to: https://github.com/FMInference/FlexGen]
askai - Command Line Interface for OpenAi ChatGPT
are-we-learning-yet - How ready is Rust for Machine Learning?
gpt_chatbot - This chatbot lets you use your microphone to communicate with GPT-4. It uses the OpenAI text to speech to respond with a voice. It uses Pinecone to store long term information and retrieves it to create context. API keys for OpenAI and Pinecone required. Tested on Windows
ggml - Tensor library for machine learning
lightseq - LightSeq: A High Performance Library for Sequence Processing and Generation
tokenizers - 💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
web-stable-diffusion - Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.