rocBLAS
whisper_real_time
rocBLAS | whisper_real_time | |
---|---|---|
6 | 4 | |
317 | 1,892 | |
2.8% | - | |
9.7 | 4.3 | |
5 days ago | about 1 month ago | |
C++ | Python | |
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.
rocBLAS
-
Nvidia DGX GH200: The First 100 Terabyte GPU Memory System
The same is also true for https://github.com/ROCmSoftwarePlatform/rocBLAS and https://github.com/ROCmSoftwarePlatform/hipBLASLt although the build stack, distribution— leaves a lot to be desired, and otherwise quite unstable.
-
Whisper.cpp v1.4.0
Full circle eh. I wonder how well it compares to just trying to use the actual Whisper models on a variety of existing Gpu capable bigger frameworks.
I don't know much practically about how hard it would be to take the Whisper PyTorch (1 or 2?) trained models & to make good use of them elsewhere. I expect Whisper.cpp probably better caters to users, is more readily consumable.
Fwiw, Whisper.cpp uses Nvidia's cuBLAS. There does appear to be an AMD rocm port. https://github.com/ROCmSoftwarePlatform/rocBLAS
-
which CPU to choose?
It's not what you asked, but I felt I should point out that rocBLAS is no longer maintained for gfx803 (the architecture of the RX 570) and PyTorch depends on rocBLAS. PyTorch will work at least to some extent, but there are known bugs that may never be fixed. I've been trying to change this, but that's how things are right now.
-
Trying to get Pytorch ROCm to work on Ubuntu 20.04 with Fiji cards
The last release that officially supported gfx803 was ROCm 3.5. All testing on that hardware ceased shortly after said release, and the code paths for that architecture have been unmaintained for nearly two years. For a specific example of a problem you may encounter, see: https://github.com/ROCmSoftwarePlatform/rocBLAS/issues/1218
- Compute Ecosystem of AMD GPUs
-
PyTorch 1.8 adds AMD ROCm support
Although the code is still there, support for (slightly) older devices are already suffering from lack of maintainence and bugs. For instance there's a bug causing gfx803 devices to produce wrong outputs starting from mid-2020, and I'm pretty sure they're never gonna fix it.
whisper_real_time
-
Meeting Voice to Text solutions?
Edit: Looks like someone did just that - https://github.com/davabase/whisper_real_time
-
What's the most efficient and accurate speech recognition library for Python?
I found OpenAI's Whisper, then this GitHub project that turns OAI's Whisper into a real-time speech recognition library, which looks nice https://github.com/davabase/whisper_real_time
-
Whisper.cpp v1.4.0
Works reasonable well in meetings.
https://github.com/davabase/whisper_real_time
-
OpenAI’s whisper module will change the game of the speech-to-text (STT) industry
I think it scales with GPU power, I've found the real time version works well with a 3080 https://github.com/davabase/whisper_real_time
What are some alternatives?
kokkos-kernels - Kokkos C++ Performance Portability Programming Ecosystem: Math Kernels - Provides BLAS, Sparse BLAS and Graph Kernels
whisper - Robust Speech Recognition via Large-Scale Weak Supervision
ROCm - AMD ROCm™ Software - GitHub Home [Moved to: https://github.com/ROCm/ROCm]
whisper-openai - Playing around with Whisper, a speech to text model by OpenAI
HIP-CPU - An implementation of HIP that works on CPUs, across OSes.
whisper.cpp - Port of OpenAI's Whisper model in C/C++
AdaptiveCpp - Implementation of SYCL and C++ standard parallelism for CPUs and GPUs from all vendors: The independent, community-driven compiler for C++-based heterogeneous programming models. Lets applications adapt themselves to all the hardware in the system - even at runtime!
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
hipBLASLt - hipBLASLt is a library that provides general matrix-matrix operations with a flexible API and extends functionalities beyond a traditional BLAS library
stdgpu - stdgpu: Efficient STL-like Data Structures on the GPU
alpaka - Abstraction Library for Parallel Kernel Acceleration :llama: