parakeet.cpp
Ultra fast and portable Parakeet implementation for on-device inference in C++ using Axiom with MPS+Unified Memory
File Explorer
Download Latest Version (.zip)- release.yml
- parakeet.pc.in
- ParakeetConfig.cmake.in
- CMakeLists.txt
- main.cpp
- README.md
- CMakeLists.txt
- main.cpp
- README.md
- CMakeLists.txt
- main.cpp
- README.md
- CMakeLists.txt
- main.c
- README.md
- CMakeLists.txt
- main.cpp
- README.md
- CMakeLists.txt
- main.cpp
- README.md
- CMakeLists.txt
- main.cpp
- README.md
- CMakeLists.txt
- main.cpp
- README.md
- CMakeLists.txt
- main.cpp
- README.md
- CMakeLists.txt
- main.cpp
- README.md
- CMakeLists.txt
- main.cpp
- README.md
- CMakeLists.txt
- main.cpp
- README.md
- CMakeLists.txt
- main.cpp
- README.md
- CMakeLists.txt
- main.cpp
- README.md
- CMakeLists.txt
- README.md
- diarize.hpp
- parakeet_c.h
- transcribe.hpp
- audio.hpp
- audio_io.hpp
- vad.hpp
- arpa_lm.hpp
- beam_search.hpp
- phrase_boost.hpp
- tdt_beam_search.hpp
- timestamp.hpp
- vocab.hpp
- config.hpp
- ctc.hpp
- encoder.hpp
- eou.hpp
- lstm.hpp
- nemotron.hpp
- rnnt.hpp
- silero_vad.hpp
- sortformer.hpp
- streaming_encoder.hpp
- tdt.hpp
- tdt_ctc.hpp
- transformer.hpp
- parakeet.hpp
- convert_nemo.py
- convert_silero_vad.py
- extract_vocab.py
- package_release.sh
- pytorch_benchmark.py
- diarize.cpp
- parakeet_c.cpp
- transcribe.cpp
- audio.cpp
- audio_io.cpp
- vad.cpp
- arpa_lm.cpp
- beam_search.cpp
- phrase_boost.cpp
- tdt_beam_search.cpp
- timestamp.cpp
- vocab.cpp
- ctc.cpp
- encoder.cpp
- eou.cpp
- lstm.cpp
- nemotron.cpp
- rnnt.cpp
- silero_vad.cpp
- sortformer.cpp
- streaming_encoder.cpp
- tdt.cpp
- tdt_ctc.cpp
- transformer.cpp
- bench.cpp
- test_all.cpp
- test_c_api.c
- dr_flac.h
- dr_mp3.h
- dr_wav.h
- stb_vorbis.c
- axiom
- .clang-format
- .gitattributes
- .gitignore
- .gitmodules
- CMakeLists.txt
- CONTRIBUTING.md
- LICENSE
- Makefile
- README.md
# Installation Guide
git clone https://github.com/Frikallo/parakeet.cpp
Downloads the entire project code from GitHub to your computer.
cd parakeet.cpp
Moves into the project folder you just downloaded.
2. Official Install Script
Easy Recommended- Python 3 Python is required to use pip.
pip install safetensors torch
Installs the package published on PyPI directly β no need to clone the source.
Pulled directly from this repo's README.
3. CMake
Mediummkdir build && cd build
Creates a folder to hold the build output and moves into it.
cmake ..
Analyzes the source code and generates build configuration files (must be run inside the build folder).
make
Compiles the code based on the generated build configuration to produce an executable.
4. Make
Medium- Git Needed to download the project code from GitHub.
- Make Usually pre-installed on Linux/macOS. On Windows, install separately (e.g. via MSYS2 or WSL).
make build
Compiles the code based on the generated build configuration to produce an executable.
make test
Compiles the code based on the generated build configuration to produce an executable.
make bench ARGS="--110m=models/model.safetensors --tdt-600m=models/tdt.safetensors"
Compiles the code based on the generated build configuration to produce an executable.
Pulled directly from this repo's README.