diff --git a/docs/doxygen/openvino_docs.xml b/docs/doxygen/openvino_docs.xml index fb898216fe7..2f906b61cac 100644 --- a/docs/doxygen/openvino_docs.xml +++ b/docs/doxygen/openvino_docs.xml @@ -189,15 +189,6 @@ limitations under the License. - - - - - - - - - diff --git a/inference-engine/samples/speech_libs_and_demos/Kaldi_SLM_conversion_tool.md b/inference-engine/samples/speech_libs_and_demos/Kaldi_SLM_conversion_tool.md deleted file mode 100644 index a429f70577f..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/Kaldi_SLM_conversion_tool.md +++ /dev/null @@ -1,45 +0,0 @@ -# Kaldi* Statistical Language Model Conversion Tool {#openvino_inference_engine_samples_speech_libs_and_demos_Kaldi_SLM_conversion_tool} - -The Kaldi* Statistical Language Model (SLM) Conversion Tool is a command-line tool that converts [Kaldi](https://kaldi-asr.org/) language model resources to the format supported by the OpenVINO™ Speech Recognition Demos. - -## Command Line - -`kaldi_slm_convertion_tool HCLG.const.fst transitions.txt words.txt slm.fst labels.bin` - -## Input Parameters - -**HCLG.fst** - -The `HCLG.const.fst` parameter is the input weighted finite-state transducer (WFST) file in the OpenFST const format. - -Most example scripts create a language model file in that format. If you have a WFST in a different OpenFST format, convert it with the following command: - -```sh -$KALDI_ROOT/tools/openfst/bin/fstconvert --fst_type=const HCLG.fst HCLG.const.fst -``` - -The source Kaldi language model file `HCLG.fst` can be found in directories like `exp/tri2b/graph_xyz`, where `tri2b` is the name of the model used for speech recognition tests. - -**transitions.txt** -The WFST transitions file describes the relations between WFST transitions and neural acoustic model outputs. This file is usually not generated by Kaldi example scripts, so you have to create it with the following command: - -```sh -$KALDI_ROOT/src/bin/show-transitions phones.txt final.mdl > transitions.txt -``` - -For this call, the `phones.txt` file is the phoneme description file, which can often be found in `data/lang/phones.txt`. -The `final.mdl` file is the neural acoustic model that is used for speech recognition. - -**words.txt** - -The `words.txt` file defines the mappings from word IDs used internally to their text representation. For many Kaldi example scripts, the file can be found in the same directory as `HCLG.fst`. - -## Output Parameters - -**slm.fst** - -The output file `slm.fst` is generated by the SLM Conversion Tool. It contains the information needed for the OpenVINO™ speech recognition demos for decoding. - -**labels.bin** - -The `labels.bin` file defines mappings from word IDs to word strings, like the `words.txt` file, but in the binary format. The OpenVINO™ speech recognition example needs the `labels.bin` file to convert recognized words into a human-readable format. diff --git a/inference-engine/samples/speech_libs_and_demos/Live_speech_recognition_demo.md b/inference-engine/samples/speech_libs_and_demos/Live_speech_recognition_demo.md deleted file mode 100644 index 778f8574a96..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/Live_speech_recognition_demo.md +++ /dev/null @@ -1,78 +0,0 @@ -# Live Speech Recognition Demo {#openvino_inference_engine_samples_speech_libs_and_demos_Live_speech_recognition_demo} - -This demo provides a GUI interface for automatic speech recognition using selected OpenVINO™ Inference Engine plugin, OpenVINO™ Feature Extraction Library, and OpenVINO™ Decoder Library. - -## How It Works - -The application transcribes audio from a WAV file and/or audio device. It supports recognition of two audio sources in parallel, for example audio coming from your microphone and audio coming from your PC (loopback). That enables use cases like audio conference or transcribing audio from an online video stream. Among other things, user can select a specific plugin to use for the recognition, set batch size, and control volume. - -The software stack used by the demo is as follows: - -![](img/sw_components.png) - -## Running - -The application main window looks like this: - -![](img/live_speech_recognition_demo_annotated.jpg) - -Refer to the sections below for instructions for particular scenarios. - -### Transcribing Speech from WAV File - -Click **Select File (9)** and navigate to the audio file using the file selection window dialog. Ensure the selected audio format is 16 kHz, 16 bit, 1 channel stored as WAV. - -Alternatively, use the audio file that is already selected upon launching the app. - -Click **Recognize (10)**. - -Transcription appear in the **Source 1** box. - -### Transcribing Speech from Audio or Video Playback (Loopback) - -Select a proper audio output device **(3)**. - -Click **Recognize (5)** and play your video or other multimedia. - -Transcription appears in the **Source 1** box. - -> **NOTE**: Loopback on Linux\* OS may need manual settings in PulseAudio Control or via a config file. - -### Transcribing Speech Captured with Microphone - -Select a microphone **(6)**. - -Click **Recognize (8)** and start speaking. - -Transcription appears in the **Source 2** box. - -### Transcribing Speech from Audio Output and Microphone at the Same Time (Audio Conference) - -Select an audio output device **(3)**. - -Select a microphone **(6)**. - -Click both **Recognize** buttons: **(5)** and **(8)**. Then start speaking. - -Transcriptions appear in both **Source 1** and **Source 2** boxes. - -> **NOTE**: Loopback on Linux OS may need manual settings in PulseAudio Control or via a config file. - -### Changing Speech Recognition Model - -Select the desired configuration from the dropdown list **(1)**. - -To reset the application to default configuration, click **Reload (2)**. - -### Controlling Volume - -Audio volume for each stream can be controlled with sliders **(4)** and **(7)**. -Current audio levels of each stream are shown in the bar on the same row as its source selector. - -### Selecting Inference Engine Plugin - -Select an Inference Engine plugin and batch size with **(11)** and **(12)**. - -## Demo Output - -The resulting transcription for each audio source is presented in the application in real time. diff --git a/inference-engine/samples/speech_libs_and_demos/Offline_speech_recognition_demo.md b/inference-engine/samples/speech_libs_and_demos/Offline_speech_recognition_demo.md deleted file mode 100644 index 10594e2c321..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/Offline_speech_recognition_demo.md +++ /dev/null @@ -1,90 +0,0 @@ -# Offline Speech Recognition Demo {#openvino_inference_engine_samples_speech_libs_and_demos_Offline_speech_recognition_demo} - -This demo provides a command-line interface for automatic speech recognition using OpenVINO™. -Components used by this executable: - -* `lspeech_s5_ext` model - Example pre-trained LibriSpeech DNN -* `speech_library.dll` (`.so`) - Open source speech recognition library that uses OpenVINO™ Inference Engine, Intel® Speech Feature Extraction and Intel® Speech Decoder libraries - -## How It Works - -The application transcribes speech from a given WAV file and outputs the text to the console. - -## Running - -The application requires two command-line parameters, which point to an audio file with speech to transcribe and a configuration file describing the resources to use for transcription. - -### Parameters for Executable - -* `-wave` - Path to input WAV to process. WAV file needs to be in the following format: RIFF WAVE PCM 16bit, 16kHz, 1 channel, with header. -* `-c`, `--config` - Path to configuration file with paths to resources and other parameters. - -Example usage: - -```sh -offline_speech_recognition_app.exe -wave="/inputAudio.wav" -c="/configFile.cfg" -``` - -### Configuration File Description - -The configuration file is an ASCII text file where: -* Parameter name and its value are separated with the space character -* Parameter and value pair ends with the end of line character - -#### Parameter Description - -| Parameter | Description | Value used for demo | -| --- | --- | --- | -| `-fe:rt:numCeps` | Number of MFCC cepstrums | *13* | -| `-fe:rt:contextLeft` | Numbers of past frames that are stacked to form input vector for neural network inference | *5* | -| `-fe:rt:contextRight` | Numbers of future frames that are stacked to form input vector for neural network inference | *5* | -| `-fe:rt:hpfBeta` | High pass filter beta coefficient, where 0.0f means no filtering | *0.0f* | -| `-fe:rt:inputDataType` | Feature extraction input format description | *INT16_16KHZ* | -| `-fe:rt:cepstralLifter` | Lifting factor | *22.0f* | -| `-fe:rt:noDct` | Flag: use DCT as final step or not | *0* | -| `-fe:rt:featureTransform` | [Kaldi](https://kaldi-asr.org/) feature transform file that normalizes stacked features for neural network inference | | -| `-dec:wfst:acousticModelFName` | Full path to the acoustic model file, for example `openvino_ir.xml`| | -| `-dec:wfst:acousticScaleFactor` | The acoustic log likelihood scaling factor | *0.1f* | -| `-dec:wfst:beamWidth` | Viterbi search beam width | *14.0f* | -| `-dec:wfst:latticeWidth` | Lattice beam width (extends the beam width) | *0.0f* | -| `-dec:wfst:nbest` | Number of n-best hypothesis to be generated | *1* | -| `-dec:wfst:confidenceAcousticScaleFactor` | Scaling parameter to factor in acoustic scores in confidence computations | *1.0f* | -| `-dec:wfst:confidenceLMScaleFactor` | Scaling parameter to factor in language model in confidence computations | *1.0f* | -| `-dec:wfst:hmmModelFName` | Full path to HMM model | | -| `-dec:wfst:fsmFName` | Full path to pronunciation model or full statically composed LM, if static composition is used | | -| `-dec:wfstotf:gramFsmFName` | Full path to grammar model | | -| `-dec:wfst:outSymsFName` | Full path to the output symbols (lexicon) filename | | -| `-dec:wfst:tokenBufferSize` | Token pool size expressed in number of DWORDs | *150000* | -| `-dec:wfstotf:traceBackLogSize` | Number of entries in traceback expressed as log2(N) | *19* | -| `-dec:wfstotf:minStableFrames` | The time expressed in frames, after which the winning hypothesis is recognized as stable and the final result can be printed | *45* | -| `-dec:wfst:maxCumulativeTokenSize` | Maximum fill rate of token buffer before token beam is adjusted to keep token buffer fill constant. Expressed as factor of buffer size (0.0, 1.0) | *0.2f* | -| `-dec:wfst:maxTokenBufferFill` | Active token count number triggering beam tightening expressed as factor of buffer size | *0.6f* | -| `-dec:wfst:maxAvgTokenBufferFill` | Average active token count number for utterance, which triggers beam tightening when exceeded. Expressed as factor of buffer size | *1.0f* | -| `-dec:wfst:tokenBufferMinFill` | Minimum fill rate of token buffer | *0.1f* | -| `-dec:wfst:pruningTighteningDelta` | Beam tightening value when token pool usage reaches the pool capacity | *1.0f* | -| `-dec:wfst:pruningRelaxationDelta` | Beam relaxation value when token pool is not meeting minimum fill ratio criterion | *0.5f* | -| `-dec:wfst:useScoreTrendForEndpointing` | Extend end pointing with acoustic feedback | *1* | -| `-dec:wfstotf:cacheLogSize` | Number of entries in LM cache expressed as log2(N) | *16* | -| `-eng:output:format` | Format of the speech recognition output | *text* | -| `-inference:contextLeft` | IE: Additional stacking option, independent from feature extraction | *0* | -| `-inference:contextRight` | IE: Additional stacking option, independent from feature extraction | *0* | -| `-inference:device` | IE: Device used for neural computations | CPU | -| `-inference:numThreads` | IE: Number of threads used by GNA in SW mode | *1* | -| `-inference:scaleFactor` | IE: Scale factor used for static quantization | *3000.0* | -| `-inference:quantizationBits` | IE: Quantization resolution in bits | *16* or *8* | - - -## Demo Output - -The resulting transcription for the sample audio file: - -```sh -[ INFO ] Using feature transformation -[ INFO ] InferenceEngine API -[ INFO ] Device info: -[ INFO ] CPU: MKLDNNPlugin -[ INFO ] Batch size: 1 -[ INFO ] Model loading time: 61.01 ms -Recognition result: -HOW ARE YOU DOING -``` diff --git a/inference-engine/samples/speech_libs_and_demos/Speech_library.md b/inference-engine/samples/speech_libs_and_demos/Speech_library.md deleted file mode 100644 index b4074471567..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/Speech_library.md +++ /dev/null @@ -1,52 +0,0 @@ -# Speech Library {#openvino_inference_engine_samples_speech_libs_and_demos_Speech_library} - -## Overview - -Speech Library provides an easy way to work with the end-to-end speech recognition pipeline. -The software stack is created to minimize effort required to build speech-enabled applications. -Speech Library wraps all of the processing blocks and exposes a simple API. The library takes care of proper initialization and data passing between all the components in the pipeline. - -Speech Library contains: - -- Two core binary libraries in the `lib` folder: Intel® Feature Extraction library and Intel® Speech Decoder -- Speech library source code in the `src` folder -- Speech library header files in the `include` folder. The library API is in the file `speech_library.h`. - -To compile the libraries, please run a `.bat/.sh` file in the root folder of speech libraries and demos, or run the demonstration script `/deployment_tools/demo/speech_recogintion.bat/sh`. - -## Architecture - -The implementation of speech recognition pipeline used in demo applications is based on classic HMM/DNN approach. - -The pipeline consists of the following stages: - -1. Mel-frequency cepstral coefficients (MFCC) feature extraction: the input audio signal or waveform is processed by Intel® Feature Extraction library to create a series of MFCC features -2. Neural acoustic scoring: the OpenVINO ™ Inference Engine transcribes the extracted features into a sequence of phonemes using a neural acoustic model -3. Language model decoding: the Intel® Speech Decoder turns the phonemes into text hypothesis. The decoding graph takes into account the grammar of the data, as well as the distribution and probabilities of contiguous specific words (n-grams) - -![](img/asr_pipeline.png) - -## Speech Library API - -The Speech Library API consists of simple routines: - -* Build recognizer pipeline -* Provide audio samples for processing -* Inform about new stable recognition result - -The flow is described below: -![](img/speech_library_api.png) - -See `/data_processing/audio/speech_recognition/include/speech_library.h` for details about the API. - -A great example on how to use the API is the source code of [offline speech recognition demo](Offline_speech_recognition_demo.md). - -## Run Your Application - -Before running compiled binary files, make sure your application can find the Inference Engine, Speech, Decoder, and Feature Extraction libraries. - -On Linux* operating systems, including Ubuntu*, the `LD_LIBRARY_PATH` environment variable is usually used to specify directories to search libraries in. - -You can update the `LD_LIBRARY_PATH` with paths to the directories in the Inference Engine installation directory where the libraries are placed. - -Please check `run_demo.sh` of offline and live speech recognition demos to learn how the `LD_LIBRARY_PATH` environment parameter can be set. diff --git a/inference-engine/samples/speech_libs_and_demos/Speech_libs_and_demos.md b/inference-engine/samples/speech_libs_and_demos/Speech_libs_and_demos.md deleted file mode 100644 index 5bd8b99d82a..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/Speech_libs_and_demos.md +++ /dev/null @@ -1,133 +0,0 @@ -# Speech Library and Speech Recognition Demos {#openvino_inference_engine_samples_speech_libs_and_demos_Speech_libs_and_demos} - -Intel® distributions of OpenVINO™ toolkit for Linux* OS and Windows* OS provide a set of libraries and demos to -demonstrate end-to-end speech recognition, as well as new acoustic and language models that can work with these demos. -The libraries are designed for preprocessing (feature extraction) to get a feature vector from a speech signal, as well -as postprocessing (decoding) to produce text from scores. Together with OpenVINO™-based neural-network speech recognition, -these libraries provide an end-to-end pipeline converting speech to text. This pipeline is demonstrated by the -end-to-end demos: - -![](img/new_speech_demos.png) - -Note that the OpenVINO™ package also includes an [automatic speech recognition sample](../speech_sample/README.md) demonstrating acoustic model inference based on Kaldi\* neural networks. The sample works with Kaldi ARK files only, 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: - -![](img/speech_sample.png) - -The main purpose of the sample is to demonstrate a variety of features and options provided by OpenVINO™ -for speech recognition neural networks. - -Find new libraries, demos, and models at `/data_processing/audio/speech_recognition`. - -> **NOTE**: These components are installed only if you select the **Inference Engine Runtime for Intel® Gaussian & Neural Accelerator** component during installation. However, the Speech Library and speech recognition demos do not require the GNA accelerator. See Hardware support for details. - -## Package Components - -The package contains the following components: - -* [Speech Library](Speech_library.md), which includes a feature extractor and decoder - -* [Offline Speech Recognition Demo](Offline_speech_recognition_demo.md), which can process wave files with recorded speech - -* [Live Speech Recognition Demo](Live_speech_recognition_demo.md), which showcases transcription from a microphone or speakers - -* [Kaldi Statistical Language Model Conversion Tool](Kaldi_SLM_conversion_tool.md), which converts custom language models to use in the decoder - -Additionally, new acoustic and language models are available in the OpenVINO™ [storage](https://storage.openvinotoolkit.org/models_contrib/speech/2021.2/librispeech_s5/). - -## Run Speech Recognition Demos with Pre-trained Models - -To download pre-trained models and build all dependencies: - -* On Linux* OS, use the shell script `/deployment_tools/demo/demo_speech_recognition.sh` - -* On Windows* OS, use the batch file `\deployment_tools\demo\demo_speech_recognition.bat` - -The script follows the steps below: - - 1. Downloads US English models trained on the LibriSpeech dataset prepared for direct usage by the Inference Engine - 2. Installs the required components - 3. Runs the command line offline demo - 4. Runs live speech recognition application with graphical interface - -If you are behind a proxy, set the following environment variables in a console session before running the script: - -* On Linux* OS: - -```sh -export http_proxy=http://{proxyHost}:{proxyPort} -export https_proxy=https://{proxyHost}:{proxyPort} -``` - -* On Windows* OS: - -```sh -set http_proxy=http://{proxyHost}:{proxyPort} -set https_proxy=https://{proxyHost}:{proxyPort} -``` - -## Hardware Support - -The provided acoustic models have been tested on a CPU, graphics processing unit (GPU), and Intel® Gaussian & Neural Accelerator (Intel® GNA), and you can switch between these targets in offline and live speech recognition demos. - -> **NOTE**: Intel® GNA is a specific low-power coprocessor, which offloads some workloads, thus saving power and CPU resources. If you use a processor supporting the GNA, such as Intel® Core™ i3-8121U and Intel® Core™ i7-1065G7, you can notice that CPU load is much lower when GNA is selected. If you selected GNA as a device for inference, and your processor does not support GNA, then execution is performed in the emulation mode (on CPU) because `GNA_AUTO` configuration option is used. -> See [the GNA plugin documentation](https://docs.openvinotoolkit.org/latest/_docs_IE_DG_supported_plugins_GNA.html) for more information. - -Speech Library provides a highly optimized implementation of preprocessing and postprocessing (feature extraction and decoding) on CPU only. - -## Custom Models Requirements - -Before running demonstration applications with custom models, follow the steps below: - -1. Build the Speech Library and demonstration application using the `demo_speech_recognition.sh/.bat` file mentioned in Run Speech Recognition Demos with Pre-trained Models -2. Train acoustic and statistical language models using the Kaldi framework (if required) -3. [Convert the acoustic model](../../../docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Kaldi.md) using Model Optimizer for Kaldi -4. [Convert the language model](Kaldi_SLM_conversion_tool.md) using the Kaldi toolkit and provided converter -5. Create a configuration file that lists all the models required for recognition -6. Copy configuration file to `{OpenVINO build folder}/data_processing/audio/speech_recognition/models/{LANG}`. The demo models are trained for US English, so use `en-us` for the `{LANG}` folder name. - -Then you can use new models in the live speech recognition demo. -To perform speech recognition using a new model and the command-line application, provide the path to the new configuration file as an input argument of the application. - -## Convert Acoustic Model with OpenVINO™ Model Optimizer for Kaldi* - -In order to convert acoustic models, the following Kaldi files are required: - -- Acoustic model file, `final.nnet` – RAW neural network without topology information -- Counts file, `pdf.counts` (if used) -- Feature transformation file, `final.feature_transform` (if used) - -For conversion steps, follow [Converting a Kaldi* Model](../../../docs/MO_DG/prepare_model/convert_model/Convert_Model_From_Kaldi.md). - -> **NOTE**: Set the path to the XML file with the converted model in the configuration file. - -## Convert Language Model with Provided Converter - -In order to convert language models, the following Kaldi files are required: -- Acoustic model with the Hidden Markov Model (HMM) topology, `final.mdl` -- Language model Weighted Finite-State Transducers (WFST) graph, `HCLG.wfst` -- Label symbol file, `words.txt`. - -All these files are required to create resources for demo applications. - -Model conversion from Kaldi requires the following steps: - -1. Save HCLG WFST as the openFST const type: - ``` - $KALDI_ROOT/tools/openfst/bin/fstconvert --fst_type=const HCLG.fst HCLG.const_fst - ``` - -2. Generate transition ID information using `phones.txt` and `final.mdl`: - ``` - $KALDI_ROOT/src/bin/show-transitions phones.txt final.mdl > transitions.txt - ``` - -3. Convert HCLG WFST using resource conversion executable: - ``` - kaldi_slm_conversion_tool HCLG.const_fst transitions.txt words.txt cl.fst labels.bin - ``` - -> **NOTE**: Put the paths to `cl.fst` and `labels.bin` files in the configuration file to use them with the Live Speech Recognition Demo Application. - -See the [offline speech recognition demo documentation](Offline_speech_recognition_demo.md) to learn about the configuration file format. - -See [Kaldi* Statistical Language Model Conversion Tool](Kaldi_SLM_conversion_tool.md) for more information on the conversion tool. diff --git a/inference-engine/samples/speech_libs_and_demos/img/asr_pipeline.png b/inference-engine/samples/speech_libs_and_demos/img/asr_pipeline.png deleted file mode 100644 index 84a631f0397..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/asr_pipeline.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:620b57920f377725860bd8a2add72a8a9f33e5c1aee3aaf560c02d91f31817e1 -size 115336 diff --git a/inference-engine/samples/speech_libs_and_demos/img/icon_1.png b/inference-engine/samples/speech_libs_and_demos/img/icon_1.png deleted file mode 100644 index 0848289692f..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/icon_1.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:844ddf108bceba2b7ca998809927aae6d463e32d5f4ee82af19e480752fac1c1 -size 658 diff --git a/inference-engine/samples/speech_libs_and_demos/img/icon_10.png b/inference-engine/samples/speech_libs_and_demos/img/icon_10.png deleted file mode 100644 index f20734dedb6..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/icon_10.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:11089fbf62b5011215a6767d83920eacc292405f013842b753e58bf5fa2555ec -size 865 diff --git a/inference-engine/samples/speech_libs_and_demos/img/icon_11.png b/inference-engine/samples/speech_libs_and_demos/img/icon_11.png deleted file mode 100644 index 2014e4cd32e..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/icon_11.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b54202be4a359184b17bfa501bd77a6efb5b66c1d5c8da7eb8e4ce53d1192cd1 -size 717 diff --git a/inference-engine/samples/speech_libs_and_demos/img/icon_12.png b/inference-engine/samples/speech_libs_and_demos/img/icon_12.png deleted file mode 100644 index 744f79b032a..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/icon_12.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:62a4231a21a63ec9e2fc186da14ed3059498e3fc4723cdca8d771622633ef92d -size 845 diff --git a/inference-engine/samples/speech_libs_and_demos/img/icon_2.png b/inference-engine/samples/speech_libs_and_demos/img/icon_2.png deleted file mode 100644 index 3bd4c0f2640..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/icon_2.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:01a0e88e53ea004212e6386b920bb5bffd7269164a3535f006c733aa0c25adf0 -size 764 diff --git a/inference-engine/samples/speech_libs_and_demos/img/icon_3.png b/inference-engine/samples/speech_libs_and_demos/img/icon_3.png deleted file mode 100644 index da109c06b11..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/icon_3.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:43c0ddfa3ff5f9edd30e03b15b0de1cdc201fb3f03ebc3f014db4c3bd0f03630 -size 802 diff --git a/inference-engine/samples/speech_libs_and_demos/img/icon_4.png b/inference-engine/samples/speech_libs_and_demos/img/icon_4.png deleted file mode 100644 index 0b73ab4c690..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/icon_4.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0103887a8cfc7fc03150762ab21fd7c1991ce9bfa8b1ae2ffc62051026e29543 -size 695 diff --git a/inference-engine/samples/speech_libs_and_demos/img/icon_5.png b/inference-engine/samples/speech_libs_and_demos/img/icon_5.png deleted file mode 100644 index 67d31c454d1..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/icon_5.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:65d16aaa28d91b4fc2c0e3ee7e570fabb03e95d9178b96bff1580b7b0ce14b03 -size 776 diff --git a/inference-engine/samples/speech_libs_and_demos/img/icon_6.png b/inference-engine/samples/speech_libs_and_demos/img/icon_6.png deleted file mode 100644 index ca86e52cd6c..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/icon_6.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8984135312b3342675bcfa20351738a97c7e795c641b377d91b6b92cd071eb62 -size 843 diff --git a/inference-engine/samples/speech_libs_and_demos/img/icon_7.png b/inference-engine/samples/speech_libs_and_demos/img/icon_7.png deleted file mode 100644 index 885e20f9aab..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/icon_7.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fd0a6dbecfb8b6fa9b7514372ff1ab3ca361dced155cbdf14ba3c7c41b7c357e -size 709 diff --git a/inference-engine/samples/speech_libs_and_demos/img/icon_8.png b/inference-engine/samples/speech_libs_and_demos/img/icon_8.png deleted file mode 100644 index 272ca19b5e6..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/icon_8.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d9775faed5d611f092bb7f7254fe1d1232bd90b0960ebd03d3fe69a24236febe -size 840 diff --git a/inference-engine/samples/speech_libs_and_demos/img/icon_9.png b/inference-engine/samples/speech_libs_and_demos/img/icon_9.png deleted file mode 100644 index 1d5d3376214..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/icon_9.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4931e6ddeeb2512e997c2fc8a51b064f4e753470d7bf6661120ff4580b7830bd -size 846 diff --git a/inference-engine/samples/speech_libs_and_demos/img/live_speech_recognition_demo_annotated.jpg b/inference-engine/samples/speech_libs_and_demos/img/live_speech_recognition_demo_annotated.jpg deleted file mode 100644 index d17c5537439..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/live_speech_recognition_demo_annotated.jpg +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b54c302e27470d139285c0958026b0b64d9f91ea41b0bf030e6be933bfd06d02 -size 86985 diff --git a/inference-engine/samples/speech_libs_and_demos/img/new_speech_demos.png b/inference-engine/samples/speech_libs_and_demos/img/new_speech_demos.png deleted file mode 100644 index d42ddbf6841..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/new_speech_demos.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a1dea7d13713a9c37bad21a1df8077d43696f67cbbab5eb1e87b92b3b91b2a29 -size 29798 diff --git a/inference-engine/samples/speech_libs_and_demos/img/speech_library_api.png b/inference-engine/samples/speech_libs_and_demos/img/speech_library_api.png deleted file mode 100644 index 79db4604f80..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/speech_library_api.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1b8a55d04d813db595af843de7dfb89f0776709ec6d1b46d795802cbe424b304 -size 20367 diff --git a/inference-engine/samples/speech_libs_and_demos/img/speech_sample.png b/inference-engine/samples/speech_libs_and_demos/img/speech_sample.png deleted file mode 100644 index f3a8f468408..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/speech_sample.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:62b8315db0436299decd3e60c7a2171d575735e405610312bb9784e6a1b0b79c -size 29120 diff --git a/inference-engine/samples/speech_libs_and_demos/img/sw_components.png b/inference-engine/samples/speech_libs_and_demos/img/sw_components.png deleted file mode 100644 index 79b066a3ef9..00000000000 --- a/inference-engine/samples/speech_libs_and_demos/img/sw_components.png +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f965a796362dc4881e1bc129e6936d582d923ae83f2d97d3798fd186f152bbc9 -size 15294