TensorRT
whisper
Our great sponsors
TensorRT | whisper | |
---|---|---|
22 | 343 | |
9,031 | 59,916 | |
3.6% | 4.7% | |
5.0 | 6.8 | |
15 days ago | 6 days ago | |
C++ | Python | |
Apache 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.
TensorRT
-
AMD MI300X 30% higher performance than Nvidia H100, even with optimized stack
> It's not rocket science to implement matrix multiplication in any GPU.
You're right, it's harder. Saying this as someone who's done more work on the former than the latter. (I have, with a team, built a rocket engine. And not your school or backyard project size, but nozzle bigger than your face kind. I've also written CUDA kernels and boy is there a big learning curve to the latter that you gotta fundamentally rethink how you view a problem. It's unquestionable why CUDA devs are paid so much. Really it's only questionable why they aren't paid more)
I know it is easy to think this problem is easy, it really looks that way. But there's an incredible amount of optimization that goes into all of this and that's what's really hard. You aren't going to get away with just N for loops for a tensor rank N. You got to chop the data up, be intelligent about it, manage memory, how you load memory, handle many data types, take into consideration different results for different FMA operations, and a whole lot more. There's a whole lot of non-obvious things that result in high optimization (maybe obvious __after__ the fact, but that's not truthfully "obvious"). The thing is, the space is so well researched and implemented that you can't get away with naive implementations, you have to be on the bleeding edge.
Then you have to do that and make it reasonably usable for the programmer too, abstracting away all of that. Cuda also has a huge head start and momentum is not a force to be reckoned with (pun intended).
Look at TensorRT[0]. The software isn't even complete and it still isn't going to cover all neural networks on all GPUs. I've had stuff work on a V100 and H100 but not an A100, then later get fixed. They even have the "Apple Advantage" in that they have control of the hardware. I'm not certain AMD will have the same advantage. We talk a lot about the difficulties of being first mover, but I think we can also recognize that momentum is an advantage of being first mover. And it isn't one to scoff at.
-
Getting SDXL-turbo running with tensorRT
(python demo_txt2img.py "a beautiful photograph of Mt. Fuji during cherry blossom"). https://github.com/NVIDIA/TensorRT/tree/release/8.6/demo/Diffusion
-
Show HN: Ollama for Linux – Run LLMs on Linux with GPU Acceleration
- https://github.com/NVIDIA/TensorRT
TVM and other compiler-based approaches seem to really perform really well and make supporting different backends really easy. A good friend who's been in this space for a while told me llama.cpp is sort of a "hand crafted" version of what these compilers could output, which I think speaks to the craftmanship Georgi and the ggml team have put into llama.cpp, but also the opportunity to "compile" versions of llama.cpp for other model architectures or platforms.
-
Nvidia Introduces TensorRT-LLM for Accelerating LLM Inference on H100/A100 GPUs
https://github.com/NVIDIA/TensorRT/issues/982
Maybe? Looks like tensorRT does work, but I couldn't find much.
-
Train Your AI Model Once and Deploy on Any Cloud
highly optimized transformer-based encoder and decoder component, supported on pytorch, tensorflow and triton
TensorRT, custom ml framework/ inference runtime from nvidia, https://developer.nvidia.com/tensorrt, but you have to port your models
- A1111 just added support for TensorRT for webui as an extension!
-
WIP - TensorRT accelerated stable diffusion img2img from mobile camera over webrtc + whisper speech to text. Interdimensional cable is here! Code: https://github.com/venetanji/videosd
It uses the nvidia demo code from: https://github.com/NVIDIA/TensorRT/tree/main/demo/Diffusion
-
[P] Get 2x Faster Transcriptions with OpenAI Whisper Large on Kernl
The traditional way to deploy a model is to export it to Onnx, then to TensorRT plan format. Each step requires its own tooling, its own mental model, and may raise some issues. The most annoying thing is that you need Microsoft or Nvidia support to get the best performances, and sometimes model support takes time. For instance, T5, a model released in 2019, is not yet correctly supported on TensorRT, in particular K/V cache is missing (soon it will be according to TensorRT maintainers, but I wrote the very same thing almost 1 year ago and then 4 months ago so… I don’t know).
-
Speeding up T5
I've tried to speed it up with TensorRT and followed this example: https://github.com/NVIDIA/TensorRT/blob/main/demo/HuggingFace/notebooks/t5.ipynb - it does give considerable speedup for batch-size=1 but it does not work with bigger batch sizes, which is useless as I can simply increase the batch-size of HuggingFace model.
- demoDiffusion on TensorRT - supports 3090, 4090, and A100
whisper
-
Why I Care Deeply About Web Accessibility And You Should Too
Let’s not talk about local models as the hardware requirements are way beyond most of these people’s reach. I have a MacBook Air with an M2 chip and 8GB of RAM and can hardly run Whisper locally, so I use this HuggingFace space.
-
How I built NotesGPT – a full-stack AI voice note app
Last week, I launched notesGPT, a free and open source voice note app that has 35,000 visitors, 7,000 users, and over 1,000 GitHub stars so far in the last week. It allows you to record a voice note, transcribes it uses Whisper, and uses Mixtral via Together to extract action items and display them in an action items view. It’s also fully open source and comes equipped with authentication, storage, vector search, action items, and is fully responsive on mobile for ease of use.
-
Ask HN: Can AI break a speech audio into individual words?
I found a pretty good discussion in the topic here:
-
WhisperSpeech – An Open Source text-to-speech system built by inverting Whisper
There is a plot of language performance on their repo: https://github.com/openai/whisper
I am not aware of a multi-lingual leaderboard for speech recognition models.
- Ask HN: AI that allows you to make phone calls in a language you don't speak?
-
Ask HN: Favorite Podcast Episodes of 2023?
I don't know how OP does it, but here's how I'd do it:
* Generate a transcript by runing Whisper against the podcast audio file: https://github.com/openai/whisper
* Upload transcript to ChatGPT and ask it to summarize.
* Automate all the above.
-
Need advice
Ahh, that makes sense. I've been building something like that, but only from other languages into English using Whisper
-
Subtitle is now open-source
Whisper already generates subtitles[0], supporting VTT and SRT so this is just a thin wrapper around that.
[0]: https://github.com/openai/whisper/blob/e58f28804528831904c3b...
-
StyleTTS2 – open-source Eleven Labs quality Text To Speech
> although it does require you to wear headphones so the bot doesn't hear itself and get interrupted.
Maybe you can rely on some sort of speaker identification to sort this out?
-
Federated Finetuning of OpenAI's Whisper on Raspberry Pi 5
v3 only comes in one flavor: large.
I don’t think you’re going to have a good time running the large model on a Pi of any kind.
The large models are 32x slower than the tiny models, roughly.[0]
I’m seeing people report that the Pi 4 can transcribe 30 seconds of audio in somewhere between 30 seconds and 60 seconds with the tiny model.
You can do the math… 32x = 16 minutes to 32 minutes to transcribe 30 seconds of audio with the large model. Not a good time for most people.
The Pi 5 could be 2x to 3x faster.
I should benchmark my Pi 4 sometime (or Pi 5, if it ever shows up).
[0]: https://github.com/openai/whisper/blob/main/README.md#availa...
What are some alternatives?
DeepSpeed - DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
vosk-api - Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
FasterTransformer - Transformer related optimization, including BERT, GPT
silero-vad - Silero VAD: pre-trained enterprise-grade Voice Activity Detector
onnx-tensorrt - ONNX-TensorRT: TensorRT backend for ONNX
buzz - Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
vllm - A high-throughput and memory-efficient inference and serving engine for LLMs
NeMo - NeMo: a framework for generative AI
openvino - OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
whisper.cpp - Port of OpenAI's Whisper model in C/C++
stable-diffusion-webui - Stable Diffusion web UI
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.