From aeb4c5b10599acde1631583ec7433f8441f688b3 Mon Sep 17 00:00:00 2001 From: Alexandre Lissy Date: Tue, 16 Jun 2020 11:22:58 +0200 Subject: [PATCH] Fix #2942: Document supported platforms --- doc/SUPPORTED_PLATFORMS.rst | 69 +++++++++++++++++++++++++++++++++++++ doc/index.rst | 2 ++ 2 files changed, 71 insertions(+) create mode 100644 doc/SUPPORTED_PLATFORMS.rst diff --git a/doc/SUPPORTED_PLATFORMS.rst b/doc/SUPPORTED_PLATFORMS.rst new file mode 100644 index 00000000..1ccfb7e3 --- /dev/null +++ b/doc/SUPPORTED_PLATFORMS.rst @@ -0,0 +1,69 @@ +.. _supported-platforms-inference: + +Supported platforms for inference +================================= + +Here we maintain the list of supported platforms for running inference. + +Linux / AMD64 without GPU +^^^^^^^^^^^^^^^^^^^^^^^^^ +* x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down inference) +* Ubuntu 14.04+ (glibc >= 2.19, libstdc++6 >= 4.8) +* Full TensorFlow runtime (``deepspeech`` packages) +* TensorFlow Lite runtime (``deepspeech-tflite`` packages) + +Linux / AMD64 with GPU +^^^^^^^^^^^^^^^^^^^^^^ +* x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down inference) +* Ubuntu 14.04+ (glibc >= 2.19, libstdc++6 >= 4.8) +* CUDA 10.0 (and capable GPU) +* Full TensorFlow runtime (``deepspeech`` packages) +* TensorFlow Lite runtime (``deepspeech-tflite`` packages) + +Linux / ARMv7 +^^^^^^^^^^^^^ +* Cortex-A53 compatible ARMv7 SoC with Neon support +* Raspbian Buster-compatible distribution +* TensorFlow Lite runtime (``deepspeech-tflite`` packages) + +Linux / Aarch64 +^^^^^^^^^^^^^^^ +* Cortex-A72 compatible Aarch64 SoC +* ARMbian Buster-compatible distribution +* TensorFlow Lite runtime (``deepspeech-tflite`` packages) + +Android / ARMv7 +^^^^^^^^^^^^^^^ +* ARMv7 SoC with Neon support +* Android 7.0-10.0 +* NDK API level >= 21 +* TensorFlow Lite runtime (``deepspeech-tflite`` packages) + +Android / Aarch64 +^^^^^^^^^^^^^^^^^ +* Aarch64 SoC +* Android 7.0-10.0 +* NDK API level >= 21 +* TensorFlow Lite runtime (``deepspeech-tflite`` packages) + +macOS / AMD64 +^^^^^^^^^^^^^ +* x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down inference) +* macOS >= 10.10 +* Full TensorFlow runtime (``deepspeech`` packages) +* TensorFlow Lite runtime (``deepspeech-tflite`` packages) + +Windows / AMD64 without GPU +^^^^^^^^^^^^^^^^^^^^^^^^^^^ +* x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down inference) +* Windows Server >= 2012 R2 ; Windows >= 8.1 +* Full TensorFlow runtime (``deepspeech`` packages) +* TensorFlow Lite runtime (``deepspeech-tflite`` packages) + +Windows / AMD64 with GPU +^^^^^^^^^^^^^^^^^^^^^^^^ +* x86-64 CPU with AVX/FMA (one can rebuild without AVX/FMA, but it might slow down inference) +* Windows Server >= 2012 R2 ; Windows >= 8.1 +* CUDA 10.0 (and capable GPU) +* Full TensorFlow runtime (``deepspeech`` packages) +* TensorFlow Lite runtime (``deepspeech-tflite`` packages) diff --git a/doc/index.rst b/doc/index.rst index 008cbaa2..9bcfe912 100644 --- a/doc/index.rst +++ b/doc/index.rst @@ -58,6 +58,8 @@ See the output of ``deepspeech -h`` for more information on the use of ``deepspe TRAINING + SUPPORTED_PLATFORMS + .. toctree:: :maxdepth: 2 :caption: Decoder and scorer