{"id":4533,"date":"2022-03-11T21:24:37","date_gmt":"2022-03-11T20:24:37","guid":{"rendered":"https:\/\/www.pschatzmann.ch\/home\/?p=4533"},"modified":"2022-03-12T08:13:07","modified_gmt":"2022-03-12T07:13:07","slug":"tf-lite-micro_speech-esp32-audio-provider","status":"publish","type":"post","link":"https:\/\/www.pschatzmann.ch\/home\/2022\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/","title":{"rendered":"TF-Lite micro_speech &#8211; An ESP32 Audio Provider using Arduino Audio Tools"},"content":{"rendered":"<p>In <a href=\"https:\/\/www.pschatzmann.ch\/home\/2022\/02\/27\/an-introduction-into-speech-recogntion-with-arduino\/\">one of my latest Blogs<\/a> I described how the API for an easy to use the micro_speech should look like. However I was struggling to make it work. So I decided to do some <strong>baby steps<\/strong> and make the existing example work first with my <a href=\"https:\/\/github.com\/pschatzmann\/arduino-audio-tools\">audio-tools library<\/a>.<\/p>\n<p>We need to implement the (missing) methods defined audio_provider.h:<\/p>\n<ul>\n<li>InitAudioRecording<\/li>\n<li>GetAudioSamples<\/li>\n<li>LatestAudioTimestamp<\/li>\n<\/ul>\n<h3>InitAudioRecording<\/h3>\n<p>Init is easy: we just need to start i2s:<\/p>\n<pre><code>TfLiteStatus InitAudioRecording(tflite::ErrorReporter* error_reporter) {\n  AudioLogger::instance().begin(Serial, AudioLogger::Info);\n  if (!g_is_audio_initialized) {\n    g_error_reporter = error_reporter;\n    g_latest_audio_timestamp = millis();\n    \/\/ Start listening for audio: MONO @ 16KHz\n    auto cfg = i2s.defaultConfig(RX_MODE);\n    cfg.channels = 1;\n    cfg.use_apll = false;\n    cfg.auto_clear = false;\n    cfg.sample_rate = kAudioSampleFrequency;\n    cfg.input_device = AUDIO_HAL_ADC_INPUT_LINE2;\n    i2s.begin(cfg);\n    g_is_audio_initialized = true;\n    g_start_time = millis();\n  }\n  return kTfLiteOk;\n}\n<\/code><\/pre>\n<h3>GetAudioSamples<\/h3>\n<p>This is easy as well, because we just need to provide the requested number of samples<\/p>\n<pre><code>TfLiteStatus GetAudioSamples(tflite::ErrorReporter* error_reporter,\n                             int start_ms, int duration_ms,\n                             int* audio_samples_size, int16_t** audio_samples) {\n  \/\/ Determine how many samples we want in total\n  const int duration_sample_count = duration_ms * (kAudioSampleFrequency \/ 1000);\n  const int duration_byte_count = duration_sample_count * 2;\n  \/\/ blocking read to provide the requested data\n  int num_read = i2s.readBytes((uint8_t*)g_audio_output_buffer, duration_byte_count);\n  if (num_read!=duration_byte_count){\n    LOGE(\"readBytes: %d-&gt;%d\",duration_byte_count, num_read);\n    return kTfLiteError;\n  }\n  \/\/ Set pointers to provide access to the audio\n  *audio_samples_size = duration_sample_count;\n  *audio_samples = g_audio_output_buffer; \n  return kTfLiteOk;\n}\n<\/code><\/pre>\n<h3>LatestAudioTimestamp<\/h3>\n<p>With this one I was struggling most. I started to provide the milliseconds since the start. But this was leading increasing slice sizes. On the BLE Sense we process 3-4 slices with each loop. Things started to work when I just provided the <strong>to be time<\/strong> for 3 frames.<\/p>\n<pre><code>\/\/ we can not provide millis() because the result type is int32_t, so we provide the milliseconds since start.\nint32_t LatestAudioTimestamp() {\n  g_latest_audio_timestamp += 60; \/\/ time for 3-4 frames\n  return g_latest_audio_timestamp;\n}\n<\/code><\/pre>\n<p>Things are not working perfectly yet, but at least the board is starting to recognize some yes and no, which is a big step forward&#8230;<br \/>\nThe full <a href=\"https:\/\/github.com\/pschatzmann\/tflite-micro-arduino-examples\/blob\/main\/examples\/micro_speech\/arduino_audio_provider.cpp\">source code can be found on Github<\/a>.<\/p>\n<p>If you compare this implementation with <a href=\"https:\/\/github.com\/pschatzmann\/tflite-micro-arduino-examples\/blob\/main\/examples\/micro_speech\/arduino_audio_provider_nano.cpp\">the original one<\/a> you can notice that the complexity could be reduced a lot!<\/p>\n","protected":false},"excerpt":{"rendered":"<p>In one of my latest Blogs I described how the API for an easy to use the micro_speech should look like. However I was struggling to make it work. So I decided to do some baby steps and make the existing example work first with my audio-tools library. We need [&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":[20,14,22],"tags":[],"class_list":["post-4533","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-arduino","category-machine-learning","category-machine-sound"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.5 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>TF-Lite micro_speech - An ESP32 Audio Provider using Arduino Audio Tools - 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\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"TF-Lite micro_speech - An ESP32 Audio Provider using Arduino Audio Tools - Phil Schatzmann\" \/>\n<meta property=\"og:description\" content=\"In one of my latest Blogs I described how the API for an easy to use the micro_speech should look like. However I was struggling to make it work. So I decided to do some baby steps and make the existing example work first with my audio-tools library. We need [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.pschatzmann.ch\/home\/2022\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/\" \/>\n<meta property=\"og:site_name\" content=\"Phil Schatzmann\" \/>\n<meta property=\"article:published_time\" content=\"2022-03-11T20:24:37+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2022-03-12T07:13:07+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\\\/03\\\/11\\\/tf-lite-micro_speech-esp32-audio-provider\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/03\\\/11\\\/tf-lite-micro_speech-esp32-audio-provider\\\/\"},\"author\":{\"name\":\"pschatzmann\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#\\\/schema\\\/person\\\/73a53638a4e34e8373405fd737dac9b1\"},\"headline\":\"TF-Lite micro_speech &#8211; An ESP32 Audio Provider using Arduino Audio Tools\",\"datePublished\":\"2022-03-11T20:24:37+00:00\",\"dateModified\":\"2022-03-12T07:13:07+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/03\\\/11\\\/tf-lite-micro_speech-esp32-audio-provider\\\/\"},\"wordCount\":206,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#\\\/schema\\\/person\\\/73a53638a4e34e8373405fd737dac9b1\"},\"image\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/03\\\/11\\\/tf-lite-micro_speech-esp32-audio-provider\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.pschatzmann.ch\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/tensorflow.png\",\"articleSection\":[\"Arduino\",\"Machine Learning\",\"Machine Sound\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/03\\\/11\\\/tf-lite-micro_speech-esp32-audio-provider\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/03\\\/11\\\/tf-lite-micro_speech-esp32-audio-provider\\\/\",\"url\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/03\\\/11\\\/tf-lite-micro_speech-esp32-audio-provider\\\/\",\"name\":\"TF-Lite micro_speech - An ESP32 Audio Provider using Arduino Audio Tools - Phil Schatzmann\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/03\\\/11\\\/tf-lite-micro_speech-esp32-audio-provider\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/03\\\/11\\\/tf-lite-micro_speech-esp32-audio-provider\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/www.pschatzmann.ch\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/tensorflow.png\",\"datePublished\":\"2022-03-11T20:24:37+00:00\",\"dateModified\":\"2022-03-12T07:13:07+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/03\\\/11\\\/tf-lite-micro_speech-esp32-audio-provider\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/03\\\/11\\\/tf-lite-micro_speech-esp32-audio-provider\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/2022\\\/03\\\/11\\\/tf-lite-micro_speech-esp32-audio-provider\\\/#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\\\/03\\\/11\\\/tf-lite-micro_speech-esp32-audio-provider\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/www.pschatzmann.ch\\\/home\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"TF-Lite micro_speech &#8211; An ESP32 Audio Provider using Arduino Audio Tools\"}]},{\"@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":"TF-Lite micro_speech - An ESP32 Audio Provider using Arduino Audio Tools - 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\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/","og_locale":"en_US","og_type":"article","og_title":"TF-Lite micro_speech - An ESP32 Audio Provider using Arduino Audio Tools - Phil Schatzmann","og_description":"In one of my latest Blogs I described how the API for an easy to use the micro_speech should look like. However I was struggling to make it work. So I decided to do some baby steps and make the existing example work first with my audio-tools library. We need [&hellip;]","og_url":"https:\/\/www.pschatzmann.ch\/home\/2022\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/","og_site_name":"Phil Schatzmann","article_published_time":"2022-03-11T20:24:37+00:00","article_modified_time":"2022-03-12T07:13:07+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\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/#article","isPartOf":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/"},"author":{"name":"pschatzmann","@id":"https:\/\/www.pschatzmann.ch\/home\/#\/schema\/person\/73a53638a4e34e8373405fd737dac9b1"},"headline":"TF-Lite micro_speech &#8211; An ESP32 Audio Provider using Arduino Audio Tools","datePublished":"2022-03-11T20:24:37+00:00","dateModified":"2022-03-12T07:13:07+00:00","mainEntityOfPage":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/"},"wordCount":206,"commentCount":0,"publisher":{"@id":"https:\/\/www.pschatzmann.ch\/home\/#\/schema\/person\/73a53638a4e34e8373405fd737dac9b1"},"image":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/#primaryimage"},"thumbnailUrl":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/02\/tensorflow.png","articleSection":["Arduino","Machine Learning","Machine Sound"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.pschatzmann.ch\/home\/2022\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/","url":"https:\/\/www.pschatzmann.ch\/home\/2022\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/","name":"TF-Lite micro_speech - An ESP32 Audio Provider using Arduino Audio Tools - Phil Schatzmann","isPartOf":{"@id":"https:\/\/www.pschatzmann.ch\/home\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/#primaryimage"},"image":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/#primaryimage"},"thumbnailUrl":"https:\/\/www.pschatzmann.ch\/wp-content\/uploads\/2022\/02\/tensorflow.png","datePublished":"2022-03-11T20:24:37+00:00","dateModified":"2022-03-12T07:13:07+00:00","breadcrumb":{"@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.pschatzmann.ch\/home\/2022\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.pschatzmann.ch\/home\/2022\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/#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\/03\/11\/tf-lite-micro_speech-esp32-audio-provider\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.pschatzmann.ch\/home\/"},{"@type":"ListItem","position":2,"name":"TF-Lite micro_speech &#8211; An ESP32 Audio Provider using Arduino Audio Tools"}]},{"@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\/4533","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=4533"}],"version-history":[{"count":11,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/posts\/4533\/revisions"}],"predecessor-version":[{"id":4544,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/posts\/4533\/revisions\/4544"}],"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=4533"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/categories?post=4533"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.pschatzmann.ch\/home\/wp-json\/wp\/v2\/tags?post=4533"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}