{"id":4546,"date":"2022-04-05T14:45:50","date_gmt":"2022-04-05T12:45:50","guid":{"rendered":"https:\/\/www.pschatzmann.ch\/home\/?p=4546"},"modified":"2022-04-08T12:58:26","modified_gmt":"2022-04-08T10:58:26","slug":"tensorflow-lite-microspeach-the-final-solution","status":"publish","type":"post","link":"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/","title":{"rendered":"Tensorflow Lite Microspeach with my Audio Tools Library &#8211; The Final Solution"},"content":{"rendered":"<p>The staring point for doing speech recognition on an Arduino based board is <a href=\"https:\/\/www.tensorflow.org\/lite\/microcontrollers\/get_started_low_level#train_a_model\">TensorFlow Light For Microcontrollers<\/a> with the example sketch called micro_speech!<\/p>\n<p>I have presented <a href=\"https:\/\/www.pschatzmann.ch\/home\/2022\/02\/27\/an-introduction-into-speech-recogntion-with-arduino\/\">a DRAFT proposal for a Micro Speach API in one of my last posts<\/a>. In the meantime I have finally managed to adapt the MicroSpeech example from <strong>TensorFlow Lite<\/strong> to follow the philosophy of <a href=\"https:\/\/github.com\/pschatzmann\/arduino-audio-tools\">my Arduino Audio Tools Library<\/a>. The example uses a <strong>Tensorflow model<\/strong> which can recognise the words &#8216;yes&#8217; and &#8216;no&#8217;. The output stream class is <a href=\"https:\/\/pschatzmann.github.io\/arduino-audio-tools\/html\/classaudio__tools_1_1_tf_lite_audio_stream.html\">TfLiteAudioStream<\/a>. In the example I am using an AudioKit, but you can replace this with any type of microphone.<\/p>\n<h2>The Arduino Sketch<\/h2>\n<p>Here is the complete Arduino Sketch. The <strong>audio source<\/strong> is the <strong>microphone<\/strong> of the audiokit and the <strong>audio sink<\/strong> is the <code>TfLiteAudioStream<\/code> class which can classify the result into 4 different outputs labels.<\/p>\n<pre><code><br \/>#include \"AudioTools.h\"\n#include \"AudioLibs\/AudioKit.h\"\n#include \"AudioLibs\/TfLiteAudioStream.h\"\n#include \"model.h\"  \/\/ tensorflow model\n\nAudioKitStream kit;  \/\/ Audio source\nTfLiteAudioStream tfl;  \/\/ Audio sink\nconst char* kCategoryLabels[4] = {\n    \"silence\",\n    \"unknown\",\n    \"yes\",\n    \"no\",\n};\nStreamCopy copier(tfl, kit);  \/\/ copy mic to tfl\nint channels = 1;\nint samples_per_second = 16000;\n\nvoid respondToCommand(const char* found_command, uint8_t score,\n                      bool is_new_command) {\n  if (is_new_command) {\n    char buffer[80];\n    sprintf(buffer, \"Result: %s, score: %d, is_new: %s\", found_command, score,\n            is_new_command ? \"true\" : \"false\");\n    Serial.println(buffer);\n  }\n}\n\nvoid setup() {\n  Serial.begin(115200);\n  AudioLogger::instance().begin(Serial, AudioLogger::Warning);\n\n  \/\/ setup Audiokit Microphone\n  auto cfg = kit.defaultConfig(RX_MODE);\n  cfg.input_device = AUDIO_HAL_ADC_INPUT_LINE2;\n  cfg.channels = channels;\n  cfg.sample_rate = samples_per_second;\n  cfg.use_apll = false;\n  cfg.auto_clear = true;\n  cfg.buffer_size = 512;\n  cfg.buffer_count = 16;\n  kit.begin(cfg);\n\n  \/\/ Setup tensorflow output\n  auto tcfg = tfl.defaultConfig();\n  tcfg.setCategories(kCategoryLabels);\n  tcfg.channels = channels;\n  tcfg.sample_rate = samples_per_second;\n  tcfg.kTensorArenaSize = 10 * 1024;\n  tcfg.respondToCommand = respondToCommand;\n  tcfg.model = g_model;\n  tfl.begin(tcfg);\n}\n\nvoid loop() { copier.copy(); }\n<\/code><\/pre>\n<p>The key information that needs to be provided as <strong>configuration for tensorflow<\/strong> are<\/p>\n<ul>\n<li>number of channels<\/li>\n<li>sample rate<\/li>\n<li>kTensorArenaSize<\/li>\n<li>a callback for handling the responses (respondToCommand)<\/li>\n<li>the model<\/li>\n<li>the labels<\/li>\n<\/ul>\n<p>Like in any other audio sketch, we just need to copy the data from the input to the output class.<\/p>\n<h2>Overall Processing Logic<\/h2>\n<p>The TfLiteAudioOutput uses <strong>Fast Fourier transform<\/strong> (FFT) to calculate the FFT result (with the length of kFeatureSliceSize) over slices (defined by kFeatureSliceStrideMs and kFeatureSliceDurationMs) of audio data. This is used to update a <strong>spectrogram<\/strong> (with the length of kFeatureSliceSize x kFeatureSliceCount). After we added 2 (kSlicesToProcess) new FFT results to the end, we let Tensorflow evaluate the updated spectrogram to calculate the classification result. These results are post-processed (in the TfLiteRecognizeCommands class) to make sure that the result is stable.<\/p>\n<h2>Dependencies<\/h2>\n<ul>\n<li><a href=\"https:\/\/github.com\/pschatzmann\/arduino-audio-tools\">Arduino Audio Tools<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/pschatzmann\/tflite-micro-arduino-examples\">tflite-micro-arduino-examples<\/a><\/li>\n<li><a href=\"https:\/\/github.com\/pschatzmann\/arduino-audiokit\">arduino-audiokit<\/a> Optional if you use an AudioKit board<\/li>\n<\/ul>\n<h2>Building the Tensorflow Model<\/h2>\n<p>Here is the relevant <a href=\"https:\/\/github.com\/pschatzmann\/arduino-audio-tools\/blob\/main\/docs\/tensorflow\/train_micro_speech_model.ipynb\">Jupyter workbook<\/a>. I am also providing the <a href=\"https:\/\/github.com\/pschatzmann\/arduino-audio-tools\/tree\/main\/docs\/tensorflow\">necessary files to run it in Docker<\/a>. Just execute <code>docker-compose up<\/code> and connect to <code>http:\/\/localhost:8888<\/code>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The staring point for doing speech recognition on an Arduino based board is TensorFlow Light For Microcontrollers with the example sketch called micro_speech! I have presented a DRAFT proposal for a Micro Speach API in one of my last posts. In the meantime I have finally managed to adapt the [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":4489,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_crdt_document":"","_import_markdown_pro_load_document_selector":0,"_import_markdown_pro_submit_text_textarea":"","_exactmetrics_skip_tracking":false,"_exactmetrics_sitenote_active":false,"_exactmetrics_sitenote_note":"","_exactmetrics_sitenote_category":0,"footnotes":""},"categories":[20,22],"tags":[28],"class_list":["post-4546","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-arduino","category-machine-sound","tag-esp32audiokit"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.5 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Tensorflow Lite Microspeach with my Audio Tools Library - The Final Solution - Phil Schatzmann<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Tensorflow Lite Microspeach with my Audio Tools Library - The Final Solution - Phil Schatzmann\" \/>\n<meta property=\"og:description\" content=\"The staring point for doing speech recognition on an Arduino based board is TensorFlow Light For Microcontrollers with the example sketch called micro_speech! I have presented a DRAFT proposal for a Micro Speach API in one of my last posts. In the meantime I have finally managed to adapt the [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/\" \/>\n<meta property=\"og:site_name\" content=\"Phil Schatzmann\" \/>\n<meta property=\"article:published_time\" content=\"2022-04-05T12:45:50+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2022-04-08T10:58:26+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/02\/tensorflow.png\" \/>\n\t<meta property=\"og:image:width\" content=\"318\" \/>\n\t<meta property=\"og:image:height\" content=\"159\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"pschatzmann\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"pschatzmann\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/04\\\/05\\\/tensorflow-lite-microspeach-the-final-solution\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/04\\\/05\\\/tensorflow-lite-microspeach-the-final-solution\\\/\"},\"author\":{\"name\":\"pschatzmann\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#\\\/schema\\\/person\\\/73a53638a4e34e8373405fd737dac9b1\"},\"headline\":\"Tensorflow Lite Microspeach with my Audio Tools Library &#8211; The Final Solution\",\"datePublished\":\"2022-04-05T12:45:50+00:00\",\"dateModified\":\"2022-04-08T10:58:26+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/04\\\/05\\\/tensorflow-lite-microspeach-the-final-solution\\\/\"},\"wordCount\":322,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#\\\/schema\\\/person\\\/73a53638a4e34e8373405fd737dac9b1\"},\"image\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/04\\\/05\\\/tensorflow-lite-microspeach-the-final-solution\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.pschatzmann.ch\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/tensorflow.png\",\"keywords\":[\"ESP32AudioKit\"],\"articleSection\":[\"Arduino\",\"Machine Sound\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/04\\\/05\\\/tensorflow-lite-microspeach-the-final-solution\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/04\\\/05\\\/tensorflow-lite-microspeach-the-final-solution\\\/\",\"url\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/04\\\/05\\\/tensorflow-lite-microspeach-the-final-solution\\\/\",\"name\":\"Tensorflow Lite Microspeach with my Audio Tools Library - The Final Solution - Phil Schatzmann\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/04\\\/05\\\/tensorflow-lite-microspeach-the-final-solution\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/04\\\/05\\\/tensorflow-lite-microspeach-the-final-solution\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.pschatzmann.ch\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/tensorflow.png\",\"datePublished\":\"2022-04-05T12:45:50+00:00\",\"dateModified\":\"2022-04-08T10:58:26+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/04\\\/05\\\/tensorflow-lite-microspeach-the-final-solution\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/04\\\/05\\\/tensorflow-lite-microspeach-the-final-solution\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/04\\\/05\\\/tensorflow-lite-microspeach-the-final-solution\\\/#primaryimage\",\"url\":\"https:\\\/\\\/www.pschatzmann.ch\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/tensorflow.png\",\"contentUrl\":\"https:\\\/\\\/www.pschatzmann.ch\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/tensorflow.png\",\"width\":318,\"height\":159},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/04\\\/05\\\/tensorflow-lite-microspeach-the-final-solution\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Tensorflow Lite Microspeach with my Audio Tools Library &#8211; The Final Solution\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#website\",\"url\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/\",\"name\":\"Phil Schatzmann Consulting\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#\\\/schema\\\/person\\\/73a53638a4e34e8373405fd737dac9b1\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":[\"Person\",\"Organization\"],\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#\\\/schema\\\/person\\\/73a53638a4e34e8373405fd737dac9b1\",\"name\":\"pschatzmann\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/wp-content\\\/uploads\\\/2022\\\/08\\\/pschatzmann.png\",\"url\":\"https:\\\/\\\/www.pschatzmann.ch\\\/wp-content\\\/uploads\\\/2022\\\/08\\\/pschatzmann.png\",\"contentUrl\":\"https:\\\/\\\/www.pschatzmann.ch\\\/wp-content\\\/uploads\\\/2022\\\/08\\\/pschatzmann.png\",\"width\":305,\"height\":305,\"caption\":\"pschatzmann\"},\"logo\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/wp-content\\\/uploads\\\/2022\\\/08\\\/pschatzmann.png\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Tensorflow Lite Microspeach with my Audio Tools Library - The Final Solution - Phil Schatzmann","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/","og_locale":"en_US","og_type":"article","og_title":"Tensorflow Lite Microspeach with my Audio Tools Library - The Final Solution - Phil Schatzmann","og_description":"The staring point for doing speech recognition on an Arduino based board is TensorFlow Light For Microcontrollers with the example sketch called micro_speech! I have presented a DRAFT proposal for a Micro Speach API in one of my last posts. In the meantime I have finally managed to adapt the [&hellip;]","og_url":"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/","og_site_name":"Phil Schatzmann","article_published_time":"2022-04-05T12:45:50+00:00","article_modified_time":"2022-04-08T10:58:26+00:00","og_image":[{"width":318,"height":159,"url":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/02\/tensorflow.png","type":"image\/png"}],"author":"pschatzmann","twitter_card":"summary_large_image","twitter_misc":{"Written by":"pschatzmann","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/#article","isPartOf":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/"},"author":{"name":"pschatzmann","@id":"https:\/\/www.pschatzmann.ch\/home\/#\/schema\/person\/73a53638a4e34e8373405fd737dac9b1"},"headline":"Tensorflow Lite Microspeach with my Audio Tools Library &#8211; The Final Solution","datePublished":"2022-04-05T12:45:50+00:00","dateModified":"2022-04-08T10:58:26+00:00","mainEntityOfPage":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/"},"wordCount":322,"commentCount":0,"publisher":{"@id":"https:\/\/www.pschatzmann.ch\/home\/#\/schema\/person\/73a53638a4e34e8373405fd737dac9b1"},"image":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/#primaryimage"},"thumbnailUrl":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/02\/tensorflow.png","keywords":["ESP32AudioKit"],"articleSection":["Arduino","Machine Sound"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/","url":"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/","name":"Tensorflow Lite Microspeach with my Audio Tools Library - The Final Solution - Phil Schatzmann","isPartOf":{"@id":"https:\/\/www.pschatzmann.ch\/home\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/#primaryimage"},"image":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/#primaryimage"},"thumbnailUrl":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/02\/tensorflow.png","datePublished":"2022-04-05T12:45:50+00:00","dateModified":"2022-04-08T10:58:26+00:00","breadcrumb":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/#primaryimage","url":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/02\/tensorflow.png","contentUrl":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/02\/tensorflow.png","width":318,"height":159},{"@type":"BreadcrumbList","@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/04\/05\/tensorflow-lite-microspeach-the-final-solution\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.pschatzmann.ch\/home\/"},{"@type":"ListItem","position":2,"name":"Tensorflow Lite Microspeach with my Audio Tools Library &#8211; The Final Solution"}]},{"@type":"WebSite","@id":"https:\/\/www.pschatzmann.ch\/home\/#website","url":"https:\/\/www.pschatzmann.ch\/home\/","name":"Phil Schatzmann Consulting","description":"","publisher":{"@id":"https:\/\/www.pschatzmann.ch\/home\/#\/schema\/person\/73a53638a4e34e8373405fd737dac9b1"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.pschatzmann.ch\/home\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":["Person","Organization"],"@id":"https:\/\/www.pschatzmann.ch\/home\/#\/schema\/person\/73a53638a4e34e8373405fd737dac9b1","name":"pschatzmann","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/08\/pschatzmann.png","url":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/08\/pschatzmann.png","contentUrl":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/08\/pschatzmann.png","width":305,"height":305,"caption":"pschatzmann"},"logo":{"@id":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/08\/pschatzmann.png"}}]}},"post_mailing_queue_ids":[],"_links":{"self":[{"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/posts\/4546","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/comments?post=4546"}],"version-history":[{"count":30,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/posts\/4546\/revisions"}],"predecessor-version":[{"id":4583,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/posts\/4546\/revisions\/4583"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/media\/4489"}],"wp:attachment":[{"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/media?parent=4546"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/categories?post=4546"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/tags?post=4546"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}