noahkay13
Re:Parakeet.cpp – Parakeet ASR inference in pure C++ with Metal GPU ac...
on Friday February 27, 2026 @12:08PM (#47182915)
The CoreML backend is WIP in Axiom and will roll over to parakeet.cpp when it's ready, the same with CUDA. FluidAudio is a great option for those building Mac-only apps, but the goal with Axiom and Parakeet.cpp is to be very portable and embeddable into almost any app. I will write C and Swift wrappers shortly, then if it's really wanted, a Python wrapper.
Re:Parakeet.cpp – Parakeet ASR inference in pure C++ with Metal GPU ac...
on Friday February 27, 2026 @11:57AM (#47182779)
On macbook pro - parakeet.cpp is very low latency, under 100ms (76ms) for 60s audio.
Re:Parakeet.cpp – Parakeet ASR inference in pure C++ with Metal GPU ac...
on Friday February 27, 2026 @03:32AM (#47178082)
Theoretically, yes? This hasent been tested but xcode has great c++ interop and the goal with Axiom and now parakeet.cpp is to be used for portable deployments so making that process easier is definitely on the roadmap.
Re:Parakeet.cpp – Parakeet ASR inference in pure C++ with Metal GPU ac...
on Thursday February 26, 2026 @10:48PM (#47176240)
I built a C++ inference engine for NVIDIA's Parakeet speech recognition models using Axiom(https://github.com/Frikallo/axiom) my tensor library.
What it does: - Runs 7 model families: offline transcription (CTC, RNNT, TDT, TDT-CTC), streaming (EOU, Nemotron), and speaker diarization (Sortformer) - Word-level timestamps - Streaming transcription from microphone input - Speaker diarization detecting up to 4 speakers
Re:Show HN: Axiom – C++ tensor library with NumPys API, optimized for ...
on Friday February 06, 2026 @01:30PM (#46916345)
I appreciate the advice. Right now, numerical coverage, absolute performance, and DX are my biggest priorities. Looking to get traction from OSS so scope creep doesn't catch up to me and some passionate devs can jump on board, autograd and CUDA are the next really big milestones for Axiom.
Show HN: Axiom – C++ tensor library with NumPys API, optimized for Apple Silicon
https://github.com/Frikallo/axiom
I kept hitting the same wall: prototype something in NumPy or PyTorch, then rewrite it in C++ for edge deployment. The rewrite always took longer than the original work. Eigen's fixed-size matrix API doesn't map to tensor workloads, xtensor is CPU-only with compile-time templated types that produce unreadable errors, and none of them have GPU support on Mac. Worse, Eigen was often slower than...
Show HN: Axiom – C++ tensor library with NumPy API and Metal GPU support
I've been building a C++ tensor library that tries to bring the ergonomics of NumPy/PyTorch to native code. The main goals were: - Familiar API (operator overloading, method chaining, same function names) - Actual GPU acceleration via Metal (not just matmul, but all ops) - Cross-platform with SIMD on x86/ARM/RISC-V via xsimd - einops-style rearrange/reduce patternsIt started because I...