Merge remote-tracking branch 'origin/main' into register/0-easyocr-wrapper.v1.0

Author: keighrim

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)

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
+    }
+  ]
+}

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"
+}

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",
@@ -65,8 +66,5 @@
   "http://apps.clams.ai/swt-detection": [
     "v1.0",
     "v2.0"
-  ],
-  "http://apps.clams.ai/easyocr-wrapper": [
-    "v1.0"
   ]
 }