From 01ee79ffb09a97ec7b9134f0b943a3d62733e116 Mon Sep 17 00:00:00 2001 From: clams-bot Date: Wed, 24 Jan 2024 05:40:09 +0000 Subject: [PATCH] adding metadata of whisper-wrapper.v4 --- docs/_apps/whisper-wrapper/v4/index.md | 56 +++++++++++++++++ docs/_apps/whisper-wrapper/v4/metadata.json | 63 +++++++++++++++++++ docs/_apps/whisper-wrapper/v4/submission.json | 6 ++ docs/_data/app-index.json | 3 +- docs/_data/apps.json | 2 +- 5 files changed, 128 insertions(+), 2 deletions(-) create mode 100644 docs/_apps/whisper-wrapper/v4/index.md create mode 100644 docs/_apps/whisper-wrapper/v4/metadata.json create mode 100644 docs/_apps/whisper-wrapper/v4/submission.json diff --git a/docs/_apps/whisper-wrapper/v4/index.md b/docs/_apps/whisper-wrapper/v4/index.md new file mode 100644 index 0000000..58979bf --- /dev/null +++ b/docs/_apps/whisper-wrapper/v4/index.md @@ -0,0 +1,56 @@ +--- +layout: single +classes: wide +title: "Whisper Wrapper (v4)" +--- +## About this version + +* Submitter: [keighrim](https://github.com/keighrim) +* Submission Time: 2024-01-24T05:40:09+00:00 +* Prebuilt Container Image: [ghcr.io/clamsproject/app-whisper-wrapper:v4](https://github.com/clamsproject/app-whisper-wrapper/pkgs/container/app-whisper-wrapper/v4) +* Release Notes + + > * updated to the latest whisper models + > * now ouputs `Sentence` annotations based on whisper's segmentation + +## About this app (See raw [metadata.json](metadata.json)) + +**A CLAMS wrapper for Whisper-based ASR software originally developed by OpenAI.** + +* App ID: [http://apps.clams.ai/whisper-wrapper/v4](http://apps.clams.ai/whisper-wrapper/v4) +* App License: Apache 2.0 +* Source Repository: [https://github.com/clamsproject/app-whisper-wrapper](https://github.com/clamsproject/app-whisper-wrapper) ([source tree of the submitted version](https://github.com/clamsproject/app-whisper-wrapper/tree/v4)) +* Analyzer Version: 20231117 +* Analyzer License: MIT + + +#### Inputs +One of the following is required: [ +* [http://mmif.clams.ai/vocabulary/AudioDocument/v1](http://mmif.clams.ai/vocabulary/AudioDocument/v1) (required) +(any properties) +* [http://mmif.clams.ai/vocabulary/VideoDocument/v1](http://mmif.clams.ai/vocabulary/VideoDocument/v1) (required) +(any properties) + + +] + + +#### Configurable Parameters +**(_Multivalued_ means the parameter can have one or more values.)** + +|Name|Description|Type|Multivalued|Default|Choices| +|----|-----------|----|-----------|-------|-------| +|modelSize|The size of the model to use. Can be "tiny", "base", "small", "medium", or "large".|string|N|tiny|**_`tiny`_**, `base`, `small`, `medium`, `large`| +|pretty|The JSON body of the HTTP response will be re-formatted with 2-space indentation|boolean|N|false|**_`false`_**, `true`| + + +#### Outputs +**(Note that not all output annotations are always generated.)** +* [http://mmif.clams.ai/vocabulary/TextDocument/v1](http://mmif.clams.ai/vocabulary/TextDocument/v1) +(any properties) +* [http://mmif.clams.ai/vocabulary/TimeFrame/v1](http://mmif.clams.ai/vocabulary/TimeFrame/v1) + * _timeUnit_ = "seconds" +* [http://mmif.clams.ai/vocabulary/Alignment/v1](http://mmif.clams.ai/vocabulary/Alignment/v1) +(any properties) +* [http://vocab.lappsgrid.org/Token](http://vocab.lappsgrid.org/Token) +(any properties) diff --git a/docs/_apps/whisper-wrapper/v4/metadata.json b/docs/_apps/whisper-wrapper/v4/metadata.json new file mode 100644 index 0000000..e50ded5 --- /dev/null +++ b/docs/_apps/whisper-wrapper/v4/metadata.json @@ -0,0 +1,63 @@ +{ + "name": "Whisper Wrapper", + "description": "A CLAMS wrapper for Whisper-based ASR software originally developed by OpenAI.", + "app_version": "v4", + "mmif_version": "1.0.0", + "analyzer_version": "20231117", + "app_license": "Apache 2.0", + "analyzer_license": "MIT", + "identifier": "http://apps.clams.ai/whisper-wrapper/v4", + "url": "https://github.com/clamsproject/app-whisper-wrapper", + "input": [ + [ + { + "@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", + "required": true + }, + { + "@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", + "required": true + } + ] + ], + "output": [ + { + "@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1" + }, + { + "@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", + "properties": { + "timeUnit": "seconds" + } + }, + { + "@type": "http://mmif.clams.ai/vocabulary/Alignment/v1" + }, + { + "@type": "http://vocab.lappsgrid.org/Token" + } + ], + "parameters": [ + { + "name": "modelSize", + "description": "The size of the model to use. Can be \"tiny\", \"base\", \"small\", \"medium\", or \"large\".", + "type": "string", + "choices": [ + "tiny", + "base", + "small", + "medium", + "large" + ], + "default": "tiny", + "multivalued": false + }, + { + "name": "pretty", + "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", + "type": "boolean", + "default": 0, + "multivalued": false + } + ] +} \ No newline at end of file diff --git a/docs/_apps/whisper-wrapper/v4/submission.json b/docs/_apps/whisper-wrapper/v4/submission.json new file mode 100644 index 0000000..474c4cf --- /dev/null +++ b/docs/_apps/whisper-wrapper/v4/submission.json @@ -0,0 +1,6 @@ +{ + "time": "2024-01-24T05:40:09+00:00", + "submitter": "keighrim", + "image": "ghcr.io/clamsproject/app-whisper-wrapper:v4", + "releasenotes": "* updated to the latest whisper models\n* now ouputs `Sentence` annotations based on whisper's segmentation\n\n" +} diff --git a/docs/_data/app-index.json b/docs/_data/app-index.json index d284935..0560fa5 100644 --- a/docs/_data/app-index.json +++ b/docs/_data/app-index.json @@ -6,7 +6,8 @@ "http://apps.clams.ai/whisper-wrapper": [ "v1", "v2", - "v3" + "v3", + "v4" ], "http://apps.clams.ai/aapb-pua-kaldi-wrapper": [ "v1", diff --git a/docs/_data/apps.json b/docs/_data/apps.json index 75b2f1b..c475c8e 100644 --- a/docs/_data/apps.json +++ b/docs/_data/apps.json @@ -1 +1 @@ -[{"name": "CLAMS wrapper for spaCy NLP", "description": "Apply spaCy NLP to all text documents in a MMIF file.", "app_version": "v1", "mmif_version": "0.5.0", "analyzer_version": "3.1.2", "app_license": "Apache 2.0", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/spacy-wrapper/v1", "url": "https://github.com/clamsproject/app-spacy-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1", "required": true}, {"@type": "http://vocab.lappsgrid.org/Token", "required": false}], "output": [{"@type": "http://vocab.lappsgrid.org/Token"}, {"@type": "http://vocab.lappsgrid.org/Token#pos"}, {"@type": "http://vocab.lappsgrid.org/Token#lemma"}, {"@type": "http://vocab.lappsgrid.org/NounChunk"}, {"@type": "http://vocab.lappsgrid.org/Sentence"}, {"@type": "http://vocab.lappsgrid.org/NamedEntity"}], "parameters": [{"name": "pretokenized", "description": "Boolean parameter to set the app to use existing tokenization, if available, for text documents for NLP processing. Useful to process ASR documents, for example.", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Whisper Wrapper", "description": "A CLAMS wrapper for Whisper-based ASR software originally developed by OpenAI.", "app_version": "v1", "mmif_version": "1.0.0", "analyzer_version": "20230314", "app_license": "Apache 2.0", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/whisper-wrapper/v1", "url": "https://github.com/clamsproject/app-whisper-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeUnit": "seconds"}}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}, {"@type": "http://vocab.lappsgrid.org/Token"}]}, {"name": "AAPB-PUA Kaldi Wrapper", "description": "A CLAMS wrapper for Kaldi-based ASR software originally developed by PopUpArchive and hipstas, and later updated by Kyeongmin Rim at Brandeis University. Wrapped software can be found at https://github.com/brandeis-llc/aapb-pua-kaldi-docker . ", "app_version": "v1", "mmif_version": "0.5.0", "analyzer_version": "v4", "app_license": "Apache 2.0", "analyzer_license": "UNKNOWN", "identifier": "http://apps.clams.ai/aapb-pua-kaldi-wrapper/v1", "url": "https://github.com/clamsproject/app-aapb-pua-kaldi-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeUnit": "milliseconds"}}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}, {"@type": "http://vocab.lappsgrid.org/Token"}], "parameters": [{"name": "use_speech_segmentation", "description": "When true, the app looks for existing TimeFrame { \"frameType\": \"speech\" } annotations, and runs ASR only on those frames, instead of entire audio files.", "type": "boolean", "default": true, "multivalued": false}]}, {"name": "Whisper Wrapper", "description": "A CLAMS wrapper for Whisper-based ASR software originally developed by OpenAI.", "app_version": "v2", "mmif_version": "1.0.0", "analyzer_version": "20230314", "app_license": "Apache 2.0", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/whisper-wrapper/v2", "url": "https://github.com/clamsproject/app-whisper-wrapper", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}]], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeUnit": "seconds"}}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}, {"@type": "http://vocab.lappsgrid.org/Token"}]}, {"name": "Brandeis ACS Wrapper", "description": "Brandeis Acoustic Classification & Segmentation (ACS) is a audio segmentation tool developed at Brandeis Lab for Linguistics and Computation. The original software can be found at https://github.com/brandeis-llc/acoustic-classification-segmentation .", "app_version": "v1", "mmif_version": "1.0.0", "analyzer_version": "1.11", "app_license": "Apache2.0", "analyzer_license": "Apache2.0", "identifier": "http://apps.clams.ai/brandeis-acs-wrapper/v1", "url": "https://github.com/clamsproject/app-brandeis-acs-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeunit": "milliseconds"}}]}, {"name": "AAPB-PUA Kaldi Wrapper", "description": "A CLAMS wrapper for Kaldi-based ASR software originally developed by PopUpArchive and hipstas, and later updated by Kyeongmin Rim at Brandeis University. Wrapped software can be found at https://github.com/brandeis-llc/aapb-pua-kaldi-docker . ", "app_version": "v2", "mmif_version": "1.0.0", "analyzer_version": "v4", "app_license": "Apache 2.0", "analyzer_license": "UNKNOWN", "identifier": "http://apps.clams.ai/aapb-pua-kaldi-wrapper/v2", "url": "https://github.com/clamsproject/app-aapb-pua-kaldi-wrapper", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}]], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeUnit": "milliseconds"}}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}, {"@type": "http://vocab.lappsgrid.org/Token"}], "parameters": [{"name": "use_speech_segmentation", "description": "When true, the app looks for existing TimeFrame { \"frameType\": \"speech\" } annotations, and runs ASR only on those frames, instead of entire audio files.", "type": "boolean", "default": true, "multivalued": false}]}, {"name": "Slate Detection", "description": "This tool detects slates.", "app_version": "v1.0", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/slatedetection/v1.0", "url": "https://github.com/clams-project/app-slatedetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"properties": {"frameType": "string"}}}], "parameters": [{"name": "timeUnit", "description": "Unit for output typeframe", "type": "string", "choices": ["frames", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop processing", "type": "integer", "default": 540000, "multivalued": false}, {"name": "stopAfterOne", "description": "When True, processing stops after first timeframe is found", "type": "boolean", "default": 1, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of frames required for a timeframe to be included in the output", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential slates.", "type": "number", "default": 0, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Pyscenedetect Wrapper", "description": "", "app_version": "v1", "mmif_version": "1.0.0", "analyzer_version": "0.6.1", "app_license": "Apache2", "analyzer_license": "BSD-3", "identifier": "http://apps.clams.ai/pyscenedetect-wrapper/v1", "url": "https://github.com/clamsproject/app-pyscenedetect-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"frameType": "shot", "timeUnit": "frame"}}], "parameters": [{"name": "mode", "description": "pick a scene detector algorithm, see http://scenedetect.com/projects/Manual/en/latest/cli/detectors.html", "type": "string", "choices": ["content", "threshold", "adaptive"], "default": "content", "multivalued": false}, {"name": "threshold", "description": "threshold value to use in the detection algorithm. Note that the meaning of this numerical value differs for different detector algorithms.", "type": "number", "default": 27, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Slate Detection", "description": "This tool detects slates.", "app_version": "v1.1", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/slatedetection/v1.1", "url": "https://github.com/clamsproject/app-slatedetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"properties": {"frameType": "string"}}}], "parameters": [{"name": "timeUnit", "description": "Unit for output typeframe", "type": "string", "choices": ["frames", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop processing", "type": "integer", "default": 540000, "multivalued": false}, {"name": "stopAfterOne", "description": "When True, processing stops after first timeframe is found", "type": "boolean", "default": 1, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of frames required for a timeframe to be included in the output", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential slates.", "type": "number", "default": 0, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Slate Detection", "description": "This tool detects slates.", "app_version": "v1.2", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/slatedetection/v1.2", "url": "https://github.com/clamsproject/app-slatedetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"properties": {"frameType": "string"}}}], "parameters": [{"name": "timeUnit", "description": "Unit for output typeframe", "type": "string", "choices": ["frames", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop processing", "type": "integer", "default": 540000, "multivalued": false}, {"name": "stopAfterOne", "description": "When True, processing stops after first timeframe is found", "type": "boolean", "default": 1, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of frames required for a timeframe to be included in the output", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential slates.", "type": "number", "default": 0, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "inaSpeechSegmenter Wrapper", "description": "inaSpeechSegmenter is a CNN-based audio segmentation toolkit. The original software can be found at https://github.com/ina-foss/inaSpeechSegmenter .", "app_version": "v1.0", "mmif_version": "1.0.0", "analyzer_version": "0.7.6", "app_license": "MIT", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/inaspeechsegmenter-wrapper/v1.0", "url": "https://github.com/clamsproject/app-inaspeechsegmenter-wrapper", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}]], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeunit": "milliseconds"}}], "parameters": [{"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Slate Detection", "description": "This tool detects slates.", "app_version": "v2.0", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/slatedetection/v2.0", "url": "https://github.com/clamsproject/app-slatedetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"properties": {"frameType": "slate"}}}], "parameters": [{"name": "timeUnit", "description": "Unit of time to use in output.", "type": "string", "choices": ["frames", "seconds", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop processing", "type": "integer", "default": 9000, "multivalued": false}, {"name": "stopAfterOne", "description": "When True, processing stops after first timeframe is found", "type": "boolean", "default": true, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of frames required for a timeframe to be included in the output", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential slates.", "type": "number", "default": 0.7, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "inaSpeechSegmenter Wrapper", "description": "inaSpeechSegmenter is a CNN-based audio segmentation toolkit. The original software can be found at https://github.com/ina-foss/inaSpeechSegmenter .", "app_version": "v1.1", "mmif_version": "1.0.0", "analyzer_version": "0.7.6", "app_license": "MIT", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/inaspeechsegmenter-wrapper/v1.1", "url": "https://github.com/clamsproject/app-inaspeechsegmenter-wrapper", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}]], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeunit": "milliseconds"}}], "parameters": [{"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Brandeis ACS Wrapper", "description": "Brandeis Acoustic Classification & Segmentation (ACS) is a audio segmentation tool developed at Brandeis Lab for Linguistics and Computation. The original software can be found at https://github.com/brandeis-llc/acoustic-classification-segmentation .", "app_version": "v2", "mmif_version": "1.0.0", "analyzer_version": "1.11", "app_license": "Apache2.0", "analyzer_license": "Apache2.0", "identifier": "http://apps.clams.ai/brandeis-acs-wrapper/v2", "url": "https://github.com/clamsproject/app-brandeis-acs-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeunit": "milliseconds"}}], "parameters": [{"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Whisper Wrapper", "description": "A CLAMS wrapper for Whisper-based ASR software originally developed by OpenAI.", "app_version": "v3", "mmif_version": "1.0.0", "analyzer_version": "20230314", "app_license": "Apache 2.0", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/whisper-wrapper/v3", "url": "https://github.com/clamsproject/app-whisper-wrapper", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}]], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeUnit": "seconds"}}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}, {"@type": "http://vocab.lappsgrid.org/Token"}], "parameters": [{"name": "modelSize", "description": "The size of the model to use. Can be \"tiny\", \"base\", \"small\", \"medium\", or \"large\".", "type": "string", "choices": ["tiny", "base", "small", "medium", "large"], "default": "tiny", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Pyscenedetect Wrapper", "description": "", "app_version": "v2", "mmif_version": "1.0.0", "analyzer_version": "0.6.1", "app_license": "Apache2", "analyzer_license": "BSD-3", "identifier": "http://apps.clams.ai/pyscenedetect-wrapper/v2", "url": "https://github.com/clamsproject/app-pyscenedetect-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"frameType": "shot", "timeUnit": "frame"}}], "parameters": [{"name": "mode", "description": "pick a scene detector algorithm, see http://scenedetect.com/projects/Manual/en/latest/cli/detectors.html", "type": "string", "choices": ["content", "threshold", "adaptive"], "default": "content", "multivalued": false}, {"name": "threshold", "description": "threshold value to use in the detection algorithm. Note that the meaning of this numerical value differs for different detector algorithms.", "type": "number", "default": 27, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "EAST Text Detection", "description": "OpenCV-based text localization app that used EAST text detection model. Please visit the source code repository for full documentation.", "app_version": "v1.0", "mmif_version": "1.0.0", "app_license": "Apache 2.0", "identifier": "http://apps.clams.ai/east-textdetection/v1.0", "url": "https://github.com/clamsproject/app-east-textdetection", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/ImageDocument/v1", "required": true}], {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "required": false}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/BoundingBox/v1", "properties": {"bboxtype": "text"}}], "parameters": [{"name": "timeUnit", "description": "Unit for time points in the output. Only works with VideoDocument input.", "type": "string", "choices": ["frames", "seconds", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "frameType", "description": "Segments of video to run on. Only works with VideoDocument input and TimeFrame input. Empty value means run on the every frame types.", "type": "string", "choices": ["", "slate", "chyron", "rolling-credit"], "default": "", "multivalued": true}, {"name": "sampleRatio", "description": "Frequency to sample frames. Only works with VideoDocument input, and without TimeFrame input. (when `TimeFrame` annotation is found, this parameter is ignored.)", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop running. Only works with VideoDocument input. The default is roughly 2 hours of video at 30fps.", "type": "integer", "default": "2 * 60 * 60 * 30", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Dbpedia Spotlight Wrapper", "description": "Apply named entity linking to all text documents in a MMIF file.", "app_version": "v1.0", "mmif_version": "1.0.0", "analyzer_version": "version_1.0", "app_license": "Apache 2.0", "analyzer_license": "Apache 2.0", "identifier": "http://apps.clams.ai/dbpedia-spotlight-wrapper/v1.0", "url": "https://github.com/clamsproject/app-dbpedia-spotlight-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1", "required": true}], "output": [{"@type": "http://vocab.lappsgrid.org/NamedEntity"}], "parameters": [{"name": "confidence", "description": "disambiguation confidence score for linking", "type": "number", "default": 0.5, "multivalued": false}, {"name": "support", "description": "resource prominence, i.e. number of in-links in Wikipedia (lower bound)", "type": "integer", "default": 0, "multivalued": false}, {"name": "types", "description": "limits recognition to certain types of named entities, e.g. DBpedia:Place", "type": "string", "multivalued": true}, {"name": "policy", "description": "(whitelist) selects all entities of the same type; (blacklist) selects all entities not of the same type", "type": "string", "choices": ["whitelist", "blacklist"], "default": "whitelist", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "CLAMS wrapper for spaCy NLP", "description": "Apply spaCy NLP to all text documents in a MMIF file.", "app_version": "v1.1", "mmif_version": "1.0.0", "analyzer_version": "3.6", "app_license": "Apache 2.0", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/spacy-wrapper/v1.1", "url": "https://github.com/clamsproject/app-spacy-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1", "required": true}, {"@type": "http://vocab.lappsgrid.org/Token", "required": false}], "output": [{"@type": "http://vocab.lappsgrid.org/Token"}, {"@type": "http://vocab.lappsgrid.org/Token#pos"}, {"@type": "http://vocab.lappsgrid.org/Token#lemma"}, {"@type": "http://vocab.lappsgrid.org/NounChunk"}, {"@type": "http://vocab.lappsgrid.org/Sentence"}, {"@type": "http://vocab.lappsgrid.org/NamedEntity"}], "parameters": [{"name": "pretokenized", "description": "Boolean parameter to set the app to use existing tokenization, if available, for text documents for NLP processing. Useful to process ASR documents, for example.", "type": "boolean", "default": 0, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Tone_Detector", "description": "Detects spans of monotonic audio within an audio file", "app_version": "v1.0", "mmif_version": "1.0.0", "app_license": "Apache 2.0", "identifier": "http://apps.clams.ai/tonedetection/v1.0", "url": "https://github.com/clamsproject/app-tonedetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"frameType": "tone"}}], "parameters": [{"name": "timeUnit", "description": "the unit for annotation output", "type": "string", "choices": ["seconds", "seconds", "milliseconds"], "default": "seconds", "multivalued": false}, {"name": "lengthThreshold", "description": "minimum length threshold (in ms)", "type": "integer", "default": 2000, "multivalued": false}, {"name": "sampleSize", "description": "length for each segment of samples to be compared", "type": "integer", "default": 512, "multivalued": false}, {"name": "stopAt", "description": "stop point for audio processing (in ms). Defaults to the length of the file", "type": "integer", "default": "None", "multivalued": false}, {"name": "tolerance", "description": "threshold value for a \"match\" within audio processing", "type": "number", "default": 1, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Gentle Forced Aligner Wrapper", "description": "This CLAMS app aligns transcript and audio track using Gentle. Gentle is a robust yet lenient forced aligner built on Kaldi.This app only works when Gentle is already installed locally.Unfortunately, Gentle is not distributed as a Python package distribution.To get Gentle installation instruction, see https://lowerquality.com/gentle/ Make sure install Gentle from the git commit specified in ``analyzer_version`` in this metadata.", "app_version": "v1.0", "mmif_version": "1.0.0", "analyzer_version": "f29245a", "app_license": "MIT", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/gentle-forced-aligner-wrapper/v1.0", "url": "https://github.com/clamsproject/app-gentle-forced-aligner-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"frameType": "speech"}, "required": false}, {"@type": "http://vocab.lappsgrid.org/Token", "required": false}], "output": [{"@type": "http://vocab.lappsgrid.org/Token"}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"frameType": "speech", "timeUnit": "milliseconds"}}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}], "parameters": [{"name": "use_speech_segmentation", "description": "When set true, use exising \"speech\"-typed ``TimeFrame`` annotations and run aligner only on those frames, instead of entire audio files.", "type": "boolean", "default": true, "multivalued": false}, {"name": "use_tokenization", "description": "When set true, ``Alignment`` annotation output will honor existing latest tokenization (``Token`` annotations). Due to a limitation of the way Kaldi reads in English tokens, existing tokens must not contain whitespaces. ", "type": "boolean", "default": true, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Chyron Detection", "description": "This tool detects chyrons, generates time segments.", "app_version": "v1.0", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/chyron-detection/v1.0", "url": "https://github.com/clamsproject/app-chyron-detection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"properties": {"frameType": "chyron"}}}], "parameters": [{"name": "timeUnit", "description": "unit for output timeframe", "type": "string", "choices": ["frames", "seconds", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames", "type": "integer", "default": 5, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of frames required for a timeframe to be included", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential chyrons", "type": "number", "default": 0.5, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Dbpedia Spotlight Wrapper", "description": "Apply named entity linking to all text documents in a MMIF file.", "app_version": "v1.1", "mmif_version": "1.0.0", "analyzer_version": "daf5309", "app_license": "Apache 2.0", "analyzer_license": "Apache 2.0", "identifier": "http://apps.clams.ai/dbpedia-spotlight-wrapper/v1.1", "url": "https://github.com/clamsproject/app-dbpedia-spotlight-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1", "required": true}], "output": [{"@type": "http://vocab.lappsgrid.org/NamedEntity"}], "parameters": [{"name": "confidence", "description": "disambiguation confidence score for linking", "type": "number", "default": 0.5, "multivalued": false}, {"name": "support", "description": "resource prominence, i.e. number of in-links in Wikipedia (lower bound)", "type": "integer", "default": 0, "multivalued": false}, {"name": "types", "description": "types filter", "type": "string", "multivalued": false}, {"name": "policy", "description": "(whitelist) selects all entities of the same type; (blacklist) selects all entities not of the same type", "type": "string", "choices": ["whitelist", "blacklist"], "default": "whitelist", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Tesseract OCR Wrapper", "description": "This tool applies Tesseract OCR to a video or image and generates text boxes and OCR results.", "app_version": "v1.0", "mmif_version": "1.0.0", "analyzer_version": "tesseract4", "app_license": "MIT", "analyzer_license": "apache", "identifier": "http://apps.clams.ai/tesseractocr-wrapper/v1.0", "url": "https://github.com/clamsproject/app-tesseractocr-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/BoundingBox/v1", "properties": {"boxType": "text"}, "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "required": false}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}], "parameters": [{"name": "frameType", "description": "Use this to specify TimeFrame to use for filtering \"text\"-typed BoundingBox annotations. Can be \"slate\", \"chyron\", \"speech\", etc.. If not set, the app won't use TimeFrames for filtering.", "type": "string", "default": "", "multivalued": true}, {"name": "threshold", "description": "Use this value between 0 and 1 to filter out low-confidence text boxes.", "type": "number", "default": 0.9, "multivalued": false}, {"name": "psm", "description": "Tesseract Page Segmentation Modes. See https://tesseract-ocr.github.io/tessdoc/ImproveQuality.html#page-segmentation-method", "type": "integer", "choices": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13], "default": 0, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Bars Detection", "description": "This tool detects SMPTE color bars.", "app_version": "v1.0", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/barsdetection/v1.0", "url": "https://github.com/clamsproject/app-barsdetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"typeSpecificProperty": {"frameType": "bars"}}}], "parameters": [{"name": "timeUnit", "description": "Unit for output typeframe.", "type": "string", "choices": ["frames", "seconds", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop processing.", "type": "integer", "default": 9000, "multivalued": false}, {"name": "stopAfterOne", "description": "When True, processing stops after first timeframe is found.", "type": "boolean", "default": true, "multivalued": false}, {"name": "minFrameCount", "description": "minimum number of frames required for a timeframe to be included in the output.", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential slates.", "type": "number", "default": 0.7, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Parseq OCR Wrapper", "description": "This tool applies Parseq OCR to a video or image and generates text boxes and OCR results.", "app_version": "v1.0", "mmif_version": "1.0.0", "analyzer_version": "bc8d95cd", "app_license": "MIT", "analyzer_license": "Apache 2.0", "identifier": "http://apps.clams.ai/parseqocr-wrapper/v1.0", "url": "https://github.com/clamsproject/app-parseqocr-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/BoundingBox/v1", "properties": {"boxType": "text"}, "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}], "parameters": [{"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "EAST Text Detection", "description": "OpenCV-based text localization app that used EAST text detection model. Please visit the source code repository for full documentation.", "app_version": "v1.1", "mmif_version": "1.0.0", "app_license": "Apache 2.0", "identifier": "http://apps.clams.ai/east-textdetection/v1.1", "url": "https://github.com/clamsproject/app-east-textdetection", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/ImageDocument/v1", "required": true}], {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "required": false}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/BoundingBox/v1", "properties": {"bboxtype": "text"}}], "parameters": [{"name": "timeUnit", "description": "Unit for time points in the output. Only works with VideoDocument input.", "type": "string", "choices": ["frames", "seconds", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "frameType", "description": "Segments of video to run on. Only works with VideoDocument input and TimeFrame input. Empty value means run on the every frame types.", "type": "string", "choices": ["", "slate", "chyron", "rolling-credit"], "default": "", "multivalued": true}, {"name": "sampleRatio", "description": "Frequency to sample frames. Only works with VideoDocument input, and without TimeFrame input. (when `TimeFrame` annotation is found, this parameter is ignored.)", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop running. Only works with VideoDocument input. The default is roughly 2 hours of video at 30fps.", "type": "integer", "default": "2 * 60 * 60 * 30", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Bars Detection", "description": "This tool detects SMPTE color bars.", "app_version": "v1.1", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/barsdetection/v1.1", "url": "https://github.com/clamsproject/app-barsdetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"typeSpecificProperty": {"frameType": "bars"}}}], "parameters": [{"name": "timeUnit", "description": "Unit for output typeframe.", "type": "string", "choices": ["frames", "seconds", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop processing.", "type": "integer", "default": 9000, "multivalued": false}, {"name": "stopAfterOne", "description": "When True, processing stops after first timeframe is found.", "type": "boolean", "default": true, "multivalued": false}, {"name": "minFrameCount", "description": "minimum number of frames required for a timeframe to be included in the output.", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential slates.", "type": "number", "default": 0.7, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Few Shot Classifier", "description": "This tool uses a vision model to classify video segments. Currenly supports \"chyron\" frame type.", "app_version": "v1.0", "mmif_version": "1.0.0", "analyzer_version": "1.0", "app_license": "MIT", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/fewshotclassifier/v1.0", "url": "https://github.com/clamsproject/app-fewshotclassifier", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"frameType": "string"}}], "parameters": [{"name": "timeUnit", "description": "Unit for output timeframe", "type": "string", "choices": ["frames", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of frames required for a timeframe to be included in the output with a minimum value of 1", "type": "integer", "default": 60, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential labels.", "type": "number", "default": 0.8, "multivalued": false}, {"name": "finetunedFrameType", "description": "Name of fine-tuned model to use. All pre-installed models are named after the frame type they were fine-tuned for.\n\nIf an empty value is passed, the app will look for fewshots.csv file in the same directory as the app.py and create a new fine-tuned model based on the examples in that file.\n\nAt the moment, a model fine-tuned on \"chyron\" frame type is shipped as pre-installed.", "type": "string", "default": "chyron", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Slate Detection", "description": "This tool detects slates.", "app_version": "v2.1", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/slatedetection/v2.1", "url": "https://github.com/clamsproject/app-slatedetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"properties": {"frameType": "slate"}}}], "parameters": [{"name": "timeUnit", "description": "Unit of time to use in output.", "type": "string", "choices": ["frames", "seconds", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop processing", "type": "integer", "default": 9000, "multivalued": false}, {"name": "stopAfterOne", "description": "When True, processing stops after first timeframe is found", "type": "boolean", "default": true, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of frames required for a timeframe to be included in the output", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential slates.", "type": "number", "default": 0.7, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Dbpedia Spotlight Wrapper", "description": "Apply named entity linking to all text documents in a MMIF file.", "app_version": "v1.2", "mmif_version": "1.0.0", "analyzer_version": "daf5309", "app_license": "Apache 2.0", "analyzer_license": "Apache 2.0", "identifier": "http://apps.clams.ai/dbpedia-spotlight-wrapper/v1.2", "url": "https://github.com/clamsproject/app-dbpedia-spotlight-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1", "required": true}], "output": [{"@type": "http://vocab.lappsgrid.org/NamedEntity"}], "parameters": [{"name": "confidence", "description": "disambiguation confidence score for linking", "type": "number", "default": 0.5, "multivalued": false}, {"name": "support", "description": "resource prominence, i.e. number of in-links in Wikipedia (lower bound)", "type": "integer", "default": 0, "multivalued": false}, {"name": "types", "description": "limits recognition to certain types of named entities, e.g. DBpedia:Place", "type": "string", "multivalued": true}, {"name": "policy", "description": "(whitelist) selects all entities of the same type; (blacklist) selects all entities not of the same type", "type": "string", "choices": ["whitelist", "blacklist"], "default": "whitelist", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Scene-with-text Detection", "description": "Detects scenes with text, like slates, chyrons and credits.", "app_version": "v1.0", "mmif_version": "1.0.0", "app_license": "Apache 2.0", "identifier": "http://apps.clams.ai/swt-detection/v1.0", "url": "https://github.com/clamsproject/app-swt-detection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1"}], "parameters": [{"name": "model", "description": "the model to use, not implemented yet", "type": "string", "default": "vgg16", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Scenes-with-text Detection", "description": "Detects scenes with text, like slates, chyrons and credits.", "app_version": "v2.0", "mmif_version": "1.0.0", "app_license": "Apache 2.0", "identifier": "http://apps.clams.ai/swt-detection/v2.0", "url": "https://github.com/clamsproject/app-swt-detection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1"}], "parameters": [{"name": "sampleRate", "description": "Milliseconds between sampled frames", "type": "integer", "default": 1000, "multivalued": false}, {"name": "minFrameScore", "description": "Minimum score for a still frame to be included in a TimeFrame", "type": "number", "default": 0.01, "multivalued": false}, {"name": "minTimeframeScore", "description": "Minimum score for a TimeFrame", "type": "number", "default": 0.25, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of sampled frames required for a TimeFrame", "type": "integer", "default": 2, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}] \ No newline at end of file +[{"name": "CLAMS wrapper for spaCy NLP", "description": "Apply spaCy NLP to all text documents in a MMIF file.", "app_version": "v1", "mmif_version": "0.5.0", "analyzer_version": "3.1.2", "app_license": "Apache 2.0", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/spacy-wrapper/v1", "url": "https://github.com/clamsproject/app-spacy-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1", "required": true}, {"@type": "http://vocab.lappsgrid.org/Token", "required": false}], "output": [{"@type": "http://vocab.lappsgrid.org/Token"}, {"@type": "http://vocab.lappsgrid.org/Token#pos"}, {"@type": "http://vocab.lappsgrid.org/Token#lemma"}, {"@type": "http://vocab.lappsgrid.org/NounChunk"}, {"@type": "http://vocab.lappsgrid.org/Sentence"}, {"@type": "http://vocab.lappsgrid.org/NamedEntity"}], "parameters": [{"name": "pretokenized", "description": "Boolean parameter to set the app to use existing tokenization, if available, for text documents for NLP processing. Useful to process ASR documents, for example.", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Whisper Wrapper", "description": "A CLAMS wrapper for Whisper-based ASR software originally developed by OpenAI.", "app_version": "v1", "mmif_version": "1.0.0", "analyzer_version": "20230314", "app_license": "Apache 2.0", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/whisper-wrapper/v1", "url": "https://github.com/clamsproject/app-whisper-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeUnit": "seconds"}}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}, {"@type": "http://vocab.lappsgrid.org/Token"}]}, {"name": "AAPB-PUA Kaldi Wrapper", "description": "A CLAMS wrapper for Kaldi-based ASR software originally developed by PopUpArchive and hipstas, and later updated by Kyeongmin Rim at Brandeis University. Wrapped software can be found at https://github.com/brandeis-llc/aapb-pua-kaldi-docker . ", "app_version": "v1", "mmif_version": "0.5.0", "analyzer_version": "v4", "app_license": "Apache 2.0", "analyzer_license": "UNKNOWN", "identifier": "http://apps.clams.ai/aapb-pua-kaldi-wrapper/v1", "url": "https://github.com/clamsproject/app-aapb-pua-kaldi-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeUnit": "milliseconds"}}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}, {"@type": "http://vocab.lappsgrid.org/Token"}], "parameters": [{"name": "use_speech_segmentation", "description": "When true, the app looks for existing TimeFrame { \"frameType\": \"speech\" } annotations, and runs ASR only on those frames, instead of entire audio files.", "type": "boolean", "default": true, "multivalued": false}]}, {"name": "Whisper Wrapper", "description": "A CLAMS wrapper for Whisper-based ASR software originally developed by OpenAI.", "app_version": "v2", "mmif_version": "1.0.0", "analyzer_version": "20230314", "app_license": "Apache 2.0", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/whisper-wrapper/v2", "url": "https://github.com/clamsproject/app-whisper-wrapper", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}]], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeUnit": "seconds"}}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}, {"@type": "http://vocab.lappsgrid.org/Token"}]}, {"name": "Brandeis ACS Wrapper", "description": "Brandeis Acoustic Classification & Segmentation (ACS) is a audio segmentation tool developed at Brandeis Lab for Linguistics and Computation. The original software can be found at https://github.com/brandeis-llc/acoustic-classification-segmentation .", "app_version": "v1", "mmif_version": "1.0.0", "analyzer_version": "1.11", "app_license": "Apache2.0", "analyzer_license": "Apache2.0", "identifier": "http://apps.clams.ai/brandeis-acs-wrapper/v1", "url": "https://github.com/clamsproject/app-brandeis-acs-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeunit": "milliseconds"}}]}, {"name": "AAPB-PUA Kaldi Wrapper", "description": "A CLAMS wrapper for Kaldi-based ASR software originally developed by PopUpArchive and hipstas, and later updated by Kyeongmin Rim at Brandeis University. Wrapped software can be found at https://github.com/brandeis-llc/aapb-pua-kaldi-docker . ", "app_version": "v2", "mmif_version": "1.0.0", "analyzer_version": "v4", "app_license": "Apache 2.0", "analyzer_license": "UNKNOWN", "identifier": "http://apps.clams.ai/aapb-pua-kaldi-wrapper/v2", "url": "https://github.com/clamsproject/app-aapb-pua-kaldi-wrapper", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}]], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeUnit": "milliseconds"}}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}, {"@type": "http://vocab.lappsgrid.org/Token"}], "parameters": [{"name": "use_speech_segmentation", "description": "When true, the app looks for existing TimeFrame { \"frameType\": \"speech\" } annotations, and runs ASR only on those frames, instead of entire audio files.", "type": "boolean", "default": true, "multivalued": false}]}, {"name": "Slate Detection", "description": "This tool detects slates.", "app_version": "v1.0", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/slatedetection/v1.0", "url": "https://github.com/clams-project/app-slatedetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"properties": {"frameType": "string"}}}], "parameters": [{"name": "timeUnit", "description": "Unit for output typeframe", "type": "string", "choices": ["frames", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop processing", "type": "integer", "default": 540000, "multivalued": false}, {"name": "stopAfterOne", "description": "When True, processing stops after first timeframe is found", "type": "boolean", "default": 1, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of frames required for a timeframe to be included in the output", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential slates.", "type": "number", "default": 0, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Pyscenedetect Wrapper", "description": "", "app_version": "v1", "mmif_version": "1.0.0", "analyzer_version": "0.6.1", "app_license": "Apache2", "analyzer_license": "BSD-3", "identifier": "http://apps.clams.ai/pyscenedetect-wrapper/v1", "url": "https://github.com/clamsproject/app-pyscenedetect-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"frameType": "shot", "timeUnit": "frame"}}], "parameters": [{"name": "mode", "description": "pick a scene detector algorithm, see http://scenedetect.com/projects/Manual/en/latest/cli/detectors.html", "type": "string", "choices": ["content", "threshold", "adaptive"], "default": "content", "multivalued": false}, {"name": "threshold", "description": "threshold value to use in the detection algorithm. Note that the meaning of this numerical value differs for different detector algorithms.", "type": "number", "default": 27, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Slate Detection", "description": "This tool detects slates.", "app_version": "v1.1", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/slatedetection/v1.1", "url": "https://github.com/clamsproject/app-slatedetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"properties": {"frameType": "string"}}}], "parameters": [{"name": "timeUnit", "description": "Unit for output typeframe", "type": "string", "choices": ["frames", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop processing", "type": "integer", "default": 540000, "multivalued": false}, {"name": "stopAfterOne", "description": "When True, processing stops after first timeframe is found", "type": "boolean", "default": 1, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of frames required for a timeframe to be included in the output", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential slates.", "type": "number", "default": 0, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Slate Detection", "description": "This tool detects slates.", "app_version": "v1.2", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/slatedetection/v1.2", "url": "https://github.com/clamsproject/app-slatedetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"properties": {"frameType": "string"}}}], "parameters": [{"name": "timeUnit", "description": "Unit for output typeframe", "type": "string", "choices": ["frames", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop processing", "type": "integer", "default": 540000, "multivalued": false}, {"name": "stopAfterOne", "description": "When True, processing stops after first timeframe is found", "type": "boolean", "default": 1, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of frames required for a timeframe to be included in the output", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential slates.", "type": "number", "default": 0, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "inaSpeechSegmenter Wrapper", "description": "inaSpeechSegmenter is a CNN-based audio segmentation toolkit. The original software can be found at https://github.com/ina-foss/inaSpeechSegmenter .", "app_version": "v1.0", "mmif_version": "1.0.0", "analyzer_version": "0.7.6", "app_license": "MIT", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/inaspeechsegmenter-wrapper/v1.0", "url": "https://github.com/clamsproject/app-inaspeechsegmenter-wrapper", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}]], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeunit": "milliseconds"}}], "parameters": [{"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Slate Detection", "description": "This tool detects slates.", "app_version": "v2.0", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/slatedetection/v2.0", "url": "https://github.com/clamsproject/app-slatedetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"properties": {"frameType": "slate"}}}], "parameters": [{"name": "timeUnit", "description": "Unit of time to use in output.", "type": "string", "choices": ["frames", "seconds", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop processing", "type": "integer", "default": 9000, "multivalued": false}, {"name": "stopAfterOne", "description": "When True, processing stops after first timeframe is found", "type": "boolean", "default": true, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of frames required for a timeframe to be included in the output", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential slates.", "type": "number", "default": 0.7, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "inaSpeechSegmenter Wrapper", "description": "inaSpeechSegmenter is a CNN-based audio segmentation toolkit. The original software can be found at https://github.com/ina-foss/inaSpeechSegmenter .", "app_version": "v1.1", "mmif_version": "1.0.0", "analyzer_version": "0.7.6", "app_license": "MIT", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/inaspeechsegmenter-wrapper/v1.1", "url": "https://github.com/clamsproject/app-inaspeechsegmenter-wrapper", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}]], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeunit": "milliseconds"}}], "parameters": [{"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Brandeis ACS Wrapper", "description": "Brandeis Acoustic Classification & Segmentation (ACS) is a audio segmentation tool developed at Brandeis Lab for Linguistics and Computation. The original software can be found at https://github.com/brandeis-llc/acoustic-classification-segmentation .", "app_version": "v2", "mmif_version": "1.0.0", "analyzer_version": "1.11", "app_license": "Apache2.0", "analyzer_license": "Apache2.0", "identifier": "http://apps.clams.ai/brandeis-acs-wrapper/v2", "url": "https://github.com/clamsproject/app-brandeis-acs-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeunit": "milliseconds"}}], "parameters": [{"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Whisper Wrapper", "description": "A CLAMS wrapper for Whisper-based ASR software originally developed by OpenAI.", "app_version": "v3", "mmif_version": "1.0.0", "analyzer_version": "20230314", "app_license": "Apache 2.0", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/whisper-wrapper/v3", "url": "https://github.com/clamsproject/app-whisper-wrapper", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}]], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeUnit": "seconds"}}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}, {"@type": "http://vocab.lappsgrid.org/Token"}], "parameters": [{"name": "modelSize", "description": "The size of the model to use. Can be \"tiny\", \"base\", \"small\", \"medium\", or \"large\".", "type": "string", "choices": ["tiny", "base", "small", "medium", "large"], "default": "tiny", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Pyscenedetect Wrapper", "description": "", "app_version": "v2", "mmif_version": "1.0.0", "analyzer_version": "0.6.1", "app_license": "Apache2", "analyzer_license": "BSD-3", "identifier": "http://apps.clams.ai/pyscenedetect-wrapper/v2", "url": "https://github.com/clamsproject/app-pyscenedetect-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"frameType": "shot", "timeUnit": "frame"}}], "parameters": [{"name": "mode", "description": "pick a scene detector algorithm, see http://scenedetect.com/projects/Manual/en/latest/cli/detectors.html", "type": "string", "choices": ["content", "threshold", "adaptive"], "default": "content", "multivalued": false}, {"name": "threshold", "description": "threshold value to use in the detection algorithm. Note that the meaning of this numerical value differs for different detector algorithms.", "type": "number", "default": 27, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "EAST Text Detection", "description": "OpenCV-based text localization app that used EAST text detection model. Please visit the source code repository for full documentation.", "app_version": "v1.0", "mmif_version": "1.0.0", "app_license": "Apache 2.0", "identifier": "http://apps.clams.ai/east-textdetection/v1.0", "url": "https://github.com/clamsproject/app-east-textdetection", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/ImageDocument/v1", "required": true}], {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "required": false}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/BoundingBox/v1", "properties": {"bboxtype": "text"}}], "parameters": [{"name": "timeUnit", "description": "Unit for time points in the output. Only works with VideoDocument input.", "type": "string", "choices": ["frames", "seconds", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "frameType", "description": "Segments of video to run on. Only works with VideoDocument input and TimeFrame input. Empty value means run on the every frame types.", "type": "string", "choices": ["", "slate", "chyron", "rolling-credit"], "default": "", "multivalued": true}, {"name": "sampleRatio", "description": "Frequency to sample frames. Only works with VideoDocument input, and without TimeFrame input. (when `TimeFrame` annotation is found, this parameter is ignored.)", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop running. Only works with VideoDocument input. The default is roughly 2 hours of video at 30fps.", "type": "integer", "default": "2 * 60 * 60 * 30", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Dbpedia Spotlight Wrapper", "description": "Apply named entity linking to all text documents in a MMIF file.", "app_version": "v1.0", "mmif_version": "1.0.0", "analyzer_version": "version_1.0", "app_license": "Apache 2.0", "analyzer_license": "Apache 2.0", "identifier": "http://apps.clams.ai/dbpedia-spotlight-wrapper/v1.0", "url": "https://github.com/clamsproject/app-dbpedia-spotlight-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1", "required": true}], "output": [{"@type": "http://vocab.lappsgrid.org/NamedEntity"}], "parameters": [{"name": "confidence", "description": "disambiguation confidence score for linking", "type": "number", "default": 0.5, "multivalued": false}, {"name": "support", "description": "resource prominence, i.e. number of in-links in Wikipedia (lower bound)", "type": "integer", "default": 0, "multivalued": false}, {"name": "types", "description": "limits recognition to certain types of named entities, e.g. DBpedia:Place", "type": "string", "multivalued": true}, {"name": "policy", "description": "(whitelist) selects all entities of the same type; (blacklist) selects all entities not of the same type", "type": "string", "choices": ["whitelist", "blacklist"], "default": "whitelist", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "CLAMS wrapper for spaCy NLP", "description": "Apply spaCy NLP to all text documents in a MMIF file.", "app_version": "v1.1", "mmif_version": "1.0.0", "analyzer_version": "3.6", "app_license": "Apache 2.0", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/spacy-wrapper/v1.1", "url": "https://github.com/clamsproject/app-spacy-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1", "required": true}, {"@type": "http://vocab.lappsgrid.org/Token", "required": false}], "output": [{"@type": "http://vocab.lappsgrid.org/Token"}, {"@type": "http://vocab.lappsgrid.org/Token#pos"}, {"@type": "http://vocab.lappsgrid.org/Token#lemma"}, {"@type": "http://vocab.lappsgrid.org/NounChunk"}, {"@type": "http://vocab.lappsgrid.org/Sentence"}, {"@type": "http://vocab.lappsgrid.org/NamedEntity"}], "parameters": [{"name": "pretokenized", "description": "Boolean parameter to set the app to use existing tokenization, if available, for text documents for NLP processing. Useful to process ASR documents, for example.", "type": "boolean", "default": 0, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Tone_Detector", "description": "Detects spans of monotonic audio within an audio file", "app_version": "v1.0", "mmif_version": "1.0.0", "app_license": "Apache 2.0", "identifier": "http://apps.clams.ai/tonedetection/v1.0", "url": "https://github.com/clamsproject/app-tonedetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"frameType": "tone"}}], "parameters": [{"name": "timeUnit", "description": "the unit for annotation output", "type": "string", "choices": ["seconds", "seconds", "milliseconds"], "default": "seconds", "multivalued": false}, {"name": "lengthThreshold", "description": "minimum length threshold (in ms)", "type": "integer", "default": 2000, "multivalued": false}, {"name": "sampleSize", "description": "length for each segment of samples to be compared", "type": "integer", "default": 512, "multivalued": false}, {"name": "stopAt", "description": "stop point for audio processing (in ms). Defaults to the length of the file", "type": "integer", "default": "None", "multivalued": false}, {"name": "tolerance", "description": "threshold value for a \"match\" within audio processing", "type": "number", "default": 1, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Gentle Forced Aligner Wrapper", "description": "This CLAMS app aligns transcript and audio track using Gentle. Gentle is a robust yet lenient forced aligner built on Kaldi.This app only works when Gentle is already installed locally.Unfortunately, Gentle is not distributed as a Python package distribution.To get Gentle installation instruction, see https://lowerquality.com/gentle/ Make sure install Gentle from the git commit specified in ``analyzer_version`` in this metadata.", "app_version": "v1.0", "mmif_version": "1.0.0", "analyzer_version": "f29245a", "app_license": "MIT", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/gentle-forced-aligner-wrapper/v1.0", "url": "https://github.com/clamsproject/app-gentle-forced-aligner-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"frameType": "speech"}, "required": false}, {"@type": "http://vocab.lappsgrid.org/Token", "required": false}], "output": [{"@type": "http://vocab.lappsgrid.org/Token"}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"frameType": "speech", "timeUnit": "milliseconds"}}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}], "parameters": [{"name": "use_speech_segmentation", "description": "When set true, use exising \"speech\"-typed ``TimeFrame`` annotations and run aligner only on those frames, instead of entire audio files.", "type": "boolean", "default": true, "multivalued": false}, {"name": "use_tokenization", "description": "When set true, ``Alignment`` annotation output will honor existing latest tokenization (``Token`` annotations). Due to a limitation of the way Kaldi reads in English tokens, existing tokens must not contain whitespaces. ", "type": "boolean", "default": true, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Chyron Detection", "description": "This tool detects chyrons, generates time segments.", "app_version": "v1.0", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/chyron-detection/v1.0", "url": "https://github.com/clamsproject/app-chyron-detection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"properties": {"frameType": "chyron"}}}], "parameters": [{"name": "timeUnit", "description": "unit for output timeframe", "type": "string", "choices": ["frames", "seconds", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames", "type": "integer", "default": 5, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of frames required for a timeframe to be included", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential chyrons", "type": "number", "default": 0.5, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Dbpedia Spotlight Wrapper", "description": "Apply named entity linking to all text documents in a MMIF file.", "app_version": "v1.1", "mmif_version": "1.0.0", "analyzer_version": "daf5309", "app_license": "Apache 2.0", "analyzer_license": "Apache 2.0", "identifier": "http://apps.clams.ai/dbpedia-spotlight-wrapper/v1.1", "url": "https://github.com/clamsproject/app-dbpedia-spotlight-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1", "required": true}], "output": [{"@type": "http://vocab.lappsgrid.org/NamedEntity"}], "parameters": [{"name": "confidence", "description": "disambiguation confidence score for linking", "type": "number", "default": 0.5, "multivalued": false}, {"name": "support", "description": "resource prominence, i.e. number of in-links in Wikipedia (lower bound)", "type": "integer", "default": 0, "multivalued": false}, {"name": "types", "description": "types filter", "type": "string", "multivalued": false}, {"name": "policy", "description": "(whitelist) selects all entities of the same type; (blacklist) selects all entities not of the same type", "type": "string", "choices": ["whitelist", "blacklist"], "default": "whitelist", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Tesseract OCR Wrapper", "description": "This tool applies Tesseract OCR to a video or image and generates text boxes and OCR results.", "app_version": "v1.0", "mmif_version": "1.0.0", "analyzer_version": "tesseract4", "app_license": "MIT", "analyzer_license": "apache", "identifier": "http://apps.clams.ai/tesseractocr-wrapper/v1.0", "url": "https://github.com/clamsproject/app-tesseractocr-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/BoundingBox/v1", "properties": {"boxType": "text"}, "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "required": false}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}], "parameters": [{"name": "frameType", "description": "Use this to specify TimeFrame to use for filtering \"text\"-typed BoundingBox annotations. Can be \"slate\", \"chyron\", \"speech\", etc.. If not set, the app won't use TimeFrames for filtering.", "type": "string", "default": "", "multivalued": true}, {"name": "threshold", "description": "Use this value between 0 and 1 to filter out low-confidence text boxes.", "type": "number", "default": 0.9, "multivalued": false}, {"name": "psm", "description": "Tesseract Page Segmentation Modes. See https://tesseract-ocr.github.io/tessdoc/ImproveQuality.html#page-segmentation-method", "type": "integer", "choices": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13], "default": 0, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Bars Detection", "description": "This tool detects SMPTE color bars.", "app_version": "v1.0", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/barsdetection/v1.0", "url": "https://github.com/clamsproject/app-barsdetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"typeSpecificProperty": {"frameType": "bars"}}}], "parameters": [{"name": "timeUnit", "description": "Unit for output typeframe.", "type": "string", "choices": ["frames", "seconds", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop processing.", "type": "integer", "default": 9000, "multivalued": false}, {"name": "stopAfterOne", "description": "When True, processing stops after first timeframe is found.", "type": "boolean", "default": true, "multivalued": false}, {"name": "minFrameCount", "description": "minimum number of frames required for a timeframe to be included in the output.", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential slates.", "type": "number", "default": 0.7, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Parseq OCR Wrapper", "description": "This tool applies Parseq OCR to a video or image and generates text boxes and OCR results.", "app_version": "v1.0", "mmif_version": "1.0.0", "analyzer_version": "bc8d95cd", "app_license": "MIT", "analyzer_license": "Apache 2.0", "identifier": "http://apps.clams.ai/parseqocr-wrapper/v1.0", "url": "https://github.com/clamsproject/app-parseqocr-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/BoundingBox/v1", "properties": {"boxType": "text"}, "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}], "parameters": [{"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "EAST Text Detection", "description": "OpenCV-based text localization app that used EAST text detection model. Please visit the source code repository for full documentation.", "app_version": "v1.1", "mmif_version": "1.0.0", "app_license": "Apache 2.0", "identifier": "http://apps.clams.ai/east-textdetection/v1.1", "url": "https://github.com/clamsproject/app-east-textdetection", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/ImageDocument/v1", "required": true}], {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "required": false}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/BoundingBox/v1", "properties": {"bboxtype": "text"}}], "parameters": [{"name": "timeUnit", "description": "Unit for time points in the output. Only works with VideoDocument input.", "type": "string", "choices": ["frames", "seconds", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "frameType", "description": "Segments of video to run on. Only works with VideoDocument input and TimeFrame input. Empty value means run on the every frame types.", "type": "string", "choices": ["", "slate", "chyron", "rolling-credit"], "default": "", "multivalued": true}, {"name": "sampleRatio", "description": "Frequency to sample frames. Only works with VideoDocument input, and without TimeFrame input. (when `TimeFrame` annotation is found, this parameter is ignored.)", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop running. Only works with VideoDocument input. The default is roughly 2 hours of video at 30fps.", "type": "integer", "default": "2 * 60 * 60 * 30", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Bars Detection", "description": "This tool detects SMPTE color bars.", "app_version": "v1.1", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/barsdetection/v1.1", "url": "https://github.com/clamsproject/app-barsdetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"typeSpecificProperty": {"frameType": "bars"}}}], "parameters": [{"name": "timeUnit", "description": "Unit for output typeframe.", "type": "string", "choices": ["frames", "seconds", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop processing.", "type": "integer", "default": 9000, "multivalued": false}, {"name": "stopAfterOne", "description": "When True, processing stops after first timeframe is found.", "type": "boolean", "default": true, "multivalued": false}, {"name": "minFrameCount", "description": "minimum number of frames required for a timeframe to be included in the output.", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential slates.", "type": "number", "default": 0.7, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Few Shot Classifier", "description": "This tool uses a vision model to classify video segments. Currenly supports \"chyron\" frame type.", "app_version": "v1.0", "mmif_version": "1.0.0", "analyzer_version": "1.0", "app_license": "MIT", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/fewshotclassifier/v1.0", "url": "https://github.com/clamsproject/app-fewshotclassifier", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"frameType": "string"}}], "parameters": [{"name": "timeUnit", "description": "Unit for output timeframe", "type": "string", "choices": ["frames", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of frames required for a timeframe to be included in the output with a minimum value of 1", "type": "integer", "default": 60, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential labels.", "type": "number", "default": 0.8, "multivalued": false}, {"name": "finetunedFrameType", "description": "Name of fine-tuned model to use. All pre-installed models are named after the frame type they were fine-tuned for.\n\nIf an empty value is passed, the app will look for fewshots.csv file in the same directory as the app.py and create a new fine-tuned model based on the examples in that file.\n\nAt the moment, a model fine-tuned on \"chyron\" frame type is shipped as pre-installed.", "type": "string", "default": "chyron", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Slate Detection", "description": "This tool detects slates.", "app_version": "v2.1", "mmif_version": "1.0.0", "app_license": "MIT", "identifier": "http://apps.clams.ai/slatedetection/v2.1", "url": "https://github.com/clamsproject/app-slatedetection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"properties": {"frameType": "slate"}}}], "parameters": [{"name": "timeUnit", "description": "Unit of time to use in output.", "type": "string", "choices": ["frames", "seconds", "milliseconds"], "default": "frames", "multivalued": false}, {"name": "sampleRatio", "description": "Frequency to sample frames.", "type": "integer", "default": 30, "multivalued": false}, {"name": "stopAt", "description": "Frame number to stop processing", "type": "integer", "default": 9000, "multivalued": false}, {"name": "stopAfterOne", "description": "When True, processing stops after first timeframe is found", "type": "boolean", "default": true, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of frames required for a timeframe to be included in the output", "type": "integer", "default": 10, "multivalued": false}, {"name": "threshold", "description": "Threshold from 0-1, lower accepts more potential slates.", "type": "number", "default": 0.7, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Dbpedia Spotlight Wrapper", "description": "Apply named entity linking to all text documents in a MMIF file.", "app_version": "v1.2", "mmif_version": "1.0.0", "analyzer_version": "daf5309", "app_license": "Apache 2.0", "analyzer_license": "Apache 2.0", "identifier": "http://apps.clams.ai/dbpedia-spotlight-wrapper/v1.2", "url": "https://github.com/clamsproject/app-dbpedia-spotlight-wrapper", "input": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1", "required": true}], "output": [{"@type": "http://vocab.lappsgrid.org/NamedEntity"}], "parameters": [{"name": "confidence", "description": "disambiguation confidence score for linking", "type": "number", "default": 0.5, "multivalued": false}, {"name": "support", "description": "resource prominence, i.e. number of in-links in Wikipedia (lower bound)", "type": "integer", "default": 0, "multivalued": false}, {"name": "types", "description": "limits recognition to certain types of named entities, e.g. DBpedia:Place", "type": "string", "multivalued": true}, {"name": "policy", "description": "(whitelist) selects all entities of the same type; (blacklist) selects all entities not of the same type", "type": "string", "choices": ["whitelist", "blacklist"], "default": "whitelist", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Scene-with-text Detection", "description": "Detects scenes with text, like slates, chyrons and credits.", "app_version": "v1.0", "mmif_version": "1.0.0", "app_license": "Apache 2.0", "identifier": "http://apps.clams.ai/swt-detection/v1.0", "url": "https://github.com/clamsproject/app-swt-detection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1"}], "parameters": [{"name": "model", "description": "the model to use, not implemented yet", "type": "string", "default": "vgg16", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Scenes-with-text Detection", "description": "Detects scenes with text, like slates, chyrons and credits.", "app_version": "v2.0", "mmif_version": "1.0.0", "app_license": "Apache 2.0", "identifier": "http://apps.clams.ai/swt-detection/v2.0", "url": "https://github.com/clamsproject/app-swt-detection", "input": [{"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1"}], "parameters": [{"name": "sampleRate", "description": "Milliseconds between sampled frames", "type": "integer", "default": 1000, "multivalued": false}, {"name": "minFrameScore", "description": "Minimum score for a still frame to be included in a TimeFrame", "type": "number", "default": 0.01, "multivalued": false}, {"name": "minTimeframeScore", "description": "Minimum score for a TimeFrame", "type": "number", "default": 0.25, "multivalued": false}, {"name": "minFrameCount", "description": "Minimum number of sampled frames required for a TimeFrame", "type": "integer", "default": 2, "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}, {"name": "Whisper Wrapper", "description": "A CLAMS wrapper for Whisper-based ASR software originally developed by OpenAI.", "app_version": "v4", "mmif_version": "1.0.0", "analyzer_version": "20231117", "app_license": "Apache 2.0", "analyzer_license": "MIT", "identifier": "http://apps.clams.ai/whisper-wrapper/v4", "url": "https://github.com/clamsproject/app-whisper-wrapper", "input": [[{"@type": "http://mmif.clams.ai/vocabulary/AudioDocument/v1", "required": true}, {"@type": "http://mmif.clams.ai/vocabulary/VideoDocument/v1", "required": true}]], "output": [{"@type": "http://mmif.clams.ai/vocabulary/TextDocument/v1"}, {"@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v1", "properties": {"timeUnit": "seconds"}}, {"@type": "http://mmif.clams.ai/vocabulary/Alignment/v1"}, {"@type": "http://vocab.lappsgrid.org/Token"}], "parameters": [{"name": "modelSize", "description": "The size of the model to use. Can be \"tiny\", \"base\", \"small\", \"medium\", or \"large\".", "type": "string", "choices": ["tiny", "base", "small", "medium", "large"], "default": "tiny", "multivalued": false}, {"name": "pretty", "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation", "type": "boolean", "default": 0, "multivalued": false}]}] \ No newline at end of file