From 06003f18d52d0ac71b864a2211f63f5d52f2be99 Mon Sep 17 00:00:00 2001 From: Karol Blaszczak Date: Fri, 25 Aug 2023 12:26:44 +0200 Subject: [PATCH] [DOCS] speech sample deprecation (#19228) --- docs/OV_Runtime_UG/supported_plugins/GNA.md | 7 +++++-- samples/cpp/speech_sample/README.md | 11 ++++++++++- samples/python/speech_sample/README.md | 9 +++++++++ 3 files changed, 24 insertions(+), 3 deletions(-) diff --git a/docs/OV_Runtime_UG/supported_plugins/GNA.md b/docs/OV_Runtime_UG/supported_plugins/GNA.md index 38dd5f6dc5e..6a0bb23cbfc 100644 --- a/docs/OV_Runtime_UG/supported_plugins/GNA.md +++ b/docs/OV_Runtime_UG/supported_plugins/GNA.md @@ -18,8 +18,11 @@ For more details on how to configure a system to use GNA, see the :doc:`GNA conf .. note:: - Intel's GNA is being discontinued and Intel® Core™ Ultra (formerly known as Meteor Lake) will be the last generation of hardware to include it. - Consider Intel's new Visual Processing Unit as a low-power solution for offloading neural network computation, for processors offering the technology. + Intel's GNA is being discontinued and Intel® Core™ Ultra (formerly known as Meteor Lake) + will be the last generation of hardware to include it. + For this reason, OpenVINO 2023.2 will also be the last version supporting the GNA plugin. + Consider Intel's new Visual Processing Unit as a low-power solution for offloading + neural network computation, for processors offering the technology. Intel® GNA Generational Differences diff --git a/samples/cpp/speech_sample/README.md b/samples/cpp/speech_sample/README.md index 188a5b43cbc..4c0823d60a2 100644 --- a/samples/cpp/speech_sample/README.md +++ b/samples/cpp/speech_sample/README.md @@ -1,5 +1,6 @@ # Automatic Speech Recognition C++ Sample {#openvino_inference_engine_samples_speech_sample_README} + @sphinxdirective .. meta:: @@ -8,6 +9,14 @@ Inference Request (C++) API. +.. note:: + + This sample is being deprecated and will no longer be maintained after + OpenVINO 2023.2 (LTS). The main reason for it is the outdated state of + the sample and its extensive usage of GNA, which is not going to be + supported by OpenVINO beyond 2023.2. + + This sample demonstrates how to execute an Asynchronous Inference of acoustic model based on Kaldi\* neural networks and speech feature vectors. The sample works with Kaldi ARK or Numpy* uncompressed NPZ files, so it does not cover an end-to-end speech recognition scenario (speech to text), requiring additional preprocessing (feature extraction) to get a feature vector from a speech signal, as well as postprocessing (decoding) to produce text from scores. @@ -21,7 +30,7 @@ The sample works with Kaldi ARK or Numpy* uncompressed NPZ files, so it does not +=============================================================+===============================================================================================================================================================+ | Validated Models | Acoustic model based on Kaldi\* neural networks (see :ref:`Model Preparation ` section) | +-------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------+ - | Model Format | OpenVINO™ toolkit Intermediate Representation (\*.xml + \*.bin) | + | Model Format | OpenVINO™ toolkit Intermediate Representation (*.xml + *.bin) | +-------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------+ | Supported devices | See :ref:`Execution Modes ` section below and :doc:`List Supported Devices ` | +-------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------+ diff --git a/samples/python/speech_sample/README.md b/samples/python/speech_sample/README.md index a4120b10ebf..55408247fc3 100644 --- a/samples/python/speech_sample/README.md +++ b/samples/python/speech_sample/README.md @@ -1,5 +1,6 @@ # Automatic Speech Recognition Python Sample {#openvino_inference_engine_ie_bridges_python_sample_speech_sample_README} + @sphinxdirective .. meta:: @@ -8,6 +9,14 @@ Inference Request (Python) API. +.. note:: + + This sample is being deprecated and will no longer be maintained after + OpenVINO 2023.2 (LTS). The main reason for it is the outdated state of + the sample and its extensive usage of GNA, which is not going to be + supported by OpenVINO beyond 2023.2. + + This sample demonstrates how to do a Synchronous Inference of acoustic model based on Kaldi\* neural models and speech feature vectors. The sample works with Kaldi ARK or Numpy* uncompressed NPZ files, so it does not cover an end-to-end speech recognition scenario (speech to text), requiring additional preprocessing (feature extraction) to get a feature vector from a speech signal, as well as postprocessing (decoding) to produce text from scores.