edalize
Whisper
Our great sponsors
edalize | Whisper | |
---|---|---|
4 | 31 | |
579 | 6,898 | |
- | - | |
7.3 | 6.5 | |
20 days ago | 5 months ago | |
Python | C++ | |
BSD 2-clause "Simplified" License | Mozilla Public License 2.0 |
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.
edalize
-
Introduction to FPGAs
Check out https://github.com/olofk/fusesoc. It gives you a command line build flow that can drive Vivado (along with many other eda tools via edalize https://github.com/olofk/edalize) without having to touch the GUI (though you might want it for programming the board, though FuseSoC can do that too).
-
Compiling Code into Silicon
This reminds me very much of edalize[1], which does something very similar.
- Olof Kindgren on LinkedIn: We have a new world record! 6000 RISC-V cores in a single chip!
Whisper
-
AMD's CDNA 3 Compute Architecture
Couple times in the past I wanted to port open source ML models from CUDA/Python to a better technology stack. I have ported Whisper https://github.com/Const-me/Whisper/ and Mistral https://github.com/Const-me/Cgml/ to D3D11. I don’t remember how much time I spent, but given both were unpaid part-time hobby projects, probably under 160 hours / each.
These software projects were great to validate the technology choices, but note I only did bare minimum to implement specific ML models. Implementing a complete PyTorch backend gonna involve dramatically more work. I can’t even estimate how much more because I’m not an expert in Python or these Python-based ML libraries.
Why would you want OpenCL? Pretty sure D3D11 compute shaders gonna be adequate for a Torch backend, and they even work on Linux with Wine: https://github.com/Const-me/Whisper/issues/42 Native Vulkan compute shaders would be even better.
Why would you want unified address space? At least in my experience, it’s often too slow to be useful. DMA transfers (CopyResource in D3D11, copy command queue in D3D12, transfer queue in VK) are implemented by dedicated hardware inside GPUs, and are way more efficient.
-
Amazon Bedrock Is Now Generally Available
https://github.com/ggerganov/whisper.cpp
https://github.com/Const-me/Whisper
I had fun with both of these. They will both do realtime transcription. Bit you will have to download the training data sets…
-
Why Nvidia Keeps Winning: The Rise of an AI Giant
Gamers don’t care about FP64 performance, and it seems nVidia is using that for market segmentation. The FP64 performance for RTX 4090 is 1.142 TFlops, for RTX 3090 Ti 0.524 TFlops. AMD doesn’t do that, FP64 performance is consistently better there, and have been this way for quite a few years. For example, the figure for 3090 Ti (a $2000 card from 2022) is similar to Radeon RX Vega 56, a $400 card from 2017 which can do 0.518 TFlops.
And another thing: nVidia forbids usage of GeForce cards in data centers, while AMD allows that. I don’t know how specifically they define datacenter, whether it’s enforceable, or whether it’s tested in courts of various jurisdictions. I just don’t want to find out answers to these questions at the legal expenses of my employer. I believe they would prefer to not cut corners like that.
I think nVidia only beats AMD due to the ecosystem: for GPGPU that’s CUDA (and especially the included first-party libraries like BLAS, FFT, DNN and others), also due to the support in popular libraries like TensorFlow. However, it’s not that hard to ignore the ecosystem, and instead write some compute shaders in HLSL. Here’s a non-trivial open-source project unrelated to CAE, where I managed to do just that with decent results: https://github.com/Const-me/Whisper That software even works on Linux, probably due to Valve’s work on DXVK 2.0 (a compatibility layer which implements D3D11 on top of Vulkan).
-
Ask HN: Any recommendations for cheap, high-quality transcription software
I just used Whisper over the weekend to transcribe 5 hours of meeting, worked nicely and it can be run on a single GPU locally. https://github.com/ggerganov/whisper.cpp
There are a few wrappers available with GUI like https://github.com/Const-me/Whisper
- Voice recognition software for German
- I built a massive search engine to find video clips by spoken text
- Is there any good free AI-based translator?
-
What are some good speech to text software?
You can try this implementation
-
Self-host Whisper As a Service with GUI and queueing. Schibsted created a transcription service for our journalists to transcribe audio interviews and podcasts really quick.
I use this wrapper on Windows. You can do either live audio, or from an audio file. Just need to download the model you want from Hugging Face. https://github.com/Const-me/Whisper
What are some alternatives?
whisper.cpp - Port of OpenAI's Whisper model in C/C++
fusesoc - Package manager and build abstraction tool for FPGA/ASIC development
skywater-pdk - Open source process design kit for usage with SkyWater Technology Foundry's 130nm node.
apio - :seedling: Open source ecosystem for open FPGA boards
freepdk-45nm - ASIC Design Kit for FreePDK45 + Nangate for use with mflowgen
whisper - Robust Speech Recognition via Large-Scale Weak Supervision
icestudio - :snowflake: Visual editor for open FPGA boards
rggen - Code generation tool for control and status registers
sphinx-vhdl
opentitan - OpenTitan: Open source silicon root of trust
hdl_checker - Repurposing existing HDL tools to help writing better code
serv - SERV - The SErial RISC-V CPU