clamsproject · keighrim · Aug 8, 2024 · Aug 8, 2024
diff --git a/docs/_apps/distil-whisper-wrapper/v1.2/index.md b/docs/_apps/distil-whisper-wrapper/v1.2/index.md
@@ -0,0 +1,98 @@
+---
+layout: posts
+classes: wide
+title: "Distil Whisper Wrapper (v1.2)"
+date: 2024-08-08T15:48:34+00:00
+---
+## About this version
+
+- Submitter: [BenLambright](https://github.com/BenLambright)
+- Submission Time: 2024-08-08T15:48:34+00:00
+- Prebuilt Container Image: [ghcr.io/clamsproject/app-distil-whisper-wrapper:v1.2](https://github.com/clamsproject/app-distil-whisper-wrapper/pkgs/container/app-distil-whisper-wrapper/v1.2)
+- Release Notes
+
+    > reverting back to HF pipeline using chunking transcription
+
+## About this app (See raw [metadata.json](metadata.json))
+
+**The wrapper of Distil-Whisper, avaliable models: distil-large-v3, distil-large-v2, distil-medium.en, distil-small.en. The default model is distil-small.en.**
+
+- App ID: [http://apps.clams.ai/distil-whisper-wrapper/v1.2](http://apps.clams.ai/distil-whisper-wrapper/v1.2)
+- App License: Apache 2.0
+- Source Repository: [https://github.com/clamsproject/app-distil-whisper-wrapper](https://github.com/clamsproject/app-distil-whisper-wrapper) ([source tree of the submitted version](https://github.com/clamsproject/app-distil-whisper-wrapper/tree/v1.2))
+- Analyzer Version: 1.0
+- Analyzer License: MIT
+
+
+#### Inputs
+(**Note**: "*" as a property value means that the property is required but can be any value.)
+
+One of the following is required: [
+- [http://mmif.clams.ai/vocabulary/AudioDocument/v1](http://mmif.clams.ai/vocabulary/AudioDocument/v1) (required)
+(of any properties)
+
+- [http://mmif.clams.ai/vocabulary/VideoDocument/v1](http://mmif.clams.ai/vocabulary/VideoDocument/v1) (required)
+(of any properties)
+
+
+
+]
+
+
+#### Configurable Parameters
+(**Note**: _Multivalued_ means the parameter can have one or more values.)
+
+- `modelSize`: optional, defaults to `distil-small.en`
+
+    - Type: string
+    - Multivalued: False
+    - Choices: `distil-large-v3`, `distil-large-v2`, `distil-medium.en`, **_`distil-small.en`_**, `small`, `s`, `medium`, `m`, `large-v2`, `l2`, `large-v3`, `l3`
+
+
+    > The size of the model to use. There are four size of model to use distil-large-v3, distil-large-v2, distil-medium.en, distil-small.en. You can also enter the abbreviation of the model as parameter. 'small' and 's' for distil-small.en; 'medium' and  'm' for distil-medium.en; 'large-v2' and 'l2' for distil-large-v2; 'large-v3' and 'l3' for distil-large-v3. The default model is distil-medium.en.)
+- `pretty`: optional, defaults to `false`
+
+    - Type: boolean
+    - Multivalued: False
+    - Choices: **_`false`_**, `true`
+
+
+    > The JSON body of the HTTP response will be re-formatted with 2-space indentation
+- `runningTime`: optional, defaults to `false`
+
+    - Type: boolean
+    - Multivalued: False
+    - Choices: **_`false`_**, `true`
+
+
+    > The running time of the app will be recorded in the view metadata
+- `hwFetch`: optional, defaults to `false`
+
+    - Type: boolean
+    - Multivalued: False
+    - Choices: **_`false`_**, `true`
+
+
+    > The hardware information (architecture, GPU and vRAM) will be recorded in the view metadata
+
+
+#### Outputs
+(**Note**: "*" as a property value means that the property is required but can be any value.)
+
+(**Note**: Not all output annotations are always generated.)
+
+- [http://mmif.clams.ai/vocabulary/TextDocument/v1](http://mmif.clams.ai/vocabulary/TextDocument/v1)
+    - _@lang_ = "en"
+
+    > Fully serialized text content of the recognized text in the input audio/video.
+- [http://mmif.clams.ai/vocabulary/TimeFrame/v5](http://mmif.clams.ai/vocabulary/TimeFrame/v5)
+    - _timeUnit_ = "milliseconds"
+
+- [http://mmif.clams.ai/vocabulary/Alignment/v1](http://mmif.clams.ai/vocabulary/Alignment/v1)
+(of any properties)
+
+    > Alignments between 1) `TimeFrame` <-> `SENTENCE`, 2) `audio/video document` <-> `TextDocument`
+- [http://vocab.lappsgrid.org/Sentence](http://vocab.lappsgrid.org/Sentence)
+(of any properties)
+
+    > The smallest recognized unit of distil-whisper. Normally a complete sentence.
diff --git a/docs/_apps/distil-whisper-wrapper/v1.2/metadata.json b/docs/_apps/distil-whisper-wrapper/v1.2/metadata.json
@@ -0,0 +1,90 @@
+{
+  "name": "Distil Whisper Wrapper",
+  "description": "The wrapper of Distil-Whisper, avaliable models: distil-large-v3, distil-large-v2, distil-medium.en, distil-small.en. The default model is distil-small.en.",
+  "app_version": "v1.2",
+  "mmif_version": "1.0.5",
+  "analyzer_version": "1.0",
+  "app_license": "Apache 2.0",
+  "analyzer_license": "MIT",
+  "identifier": "http://apps.clams.ai/distil-whisper-wrapper/v1.2",
+  "url": "https://github.com/clamsproject/app-distil-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",
+      "description": "Fully serialized text content of the recognized text in the input audio/video.",
+      "properties": {
+        "@lang": "en"
+      }
+    },
+    {
+      "@type": "http://mmif.clams.ai/vocabulary/TimeFrame/v5",
+      "properties": {
+        "timeUnit": "milliseconds"
+      }
+    },
+    {
+      "@type": "http://mmif.clams.ai/vocabulary/Alignment/v1",
+      "description": "Alignments between 1) `TimeFrame` <-> `SENTENCE`, 2) `audio/video document` <-> `TextDocument`"
+    },
+    {
+      "@type": "http://vocab.lappsgrid.org/Sentence",
+      "description": "The smallest recognized unit of distil-whisper. Normally a complete sentence."
+    }
+  ],
+  "parameters": [
+    {
+      "name": "modelSize",
+      "description": "The size of the model to use. There are four size of model to use distil-large-v3, distil-large-v2, distil-medium.en, distil-small.en. You can also enter the abbreviation of the model as parameter. 'small' and 's' for distil-small.en; 'medium' and  'm' for distil-medium.en; 'large-v2' and 'l2' for distil-large-v2; 'large-v3' and 'l3' for distil-large-v3. The default model is distil-medium.en.)",
+      "type": "string",
+      "choices": [
+        "distil-large-v3",
+        "distil-large-v2",
+        "distil-medium.en",
+        "distil-small.en",
+        "small",
+        "s",
+        "medium",
+        "m",
+        "large-v2",
+        "l2",
+        "large-v3",
+        "l3"
+      ],
+      "default": "distil-small.en",
+      "multivalued": false
+    },
+    {
+      "name": "pretty",
+      "description": "The JSON body of the HTTP response will be re-formatted with 2-space indentation",
+      "type": "boolean",
+      "default": false,
+      "multivalued": false
+    },
+    {
+      "name": "runningTime",
+      "description": "The running time of the app will be recorded in the view metadata",
+      "type": "boolean",
+      "default": false,
+      "multivalued": false
+    },
+    {
+      "name": "hwFetch",
+      "description": "The hardware information (architecture, GPU and vRAM) will be recorded in the view metadata",
+      "type": "boolean",
+      "default": false,
+      "multivalued": false
+    }
+  ]
+}
diff --git a/docs/_apps/distil-whisper-wrapper/v1.2/submission.json b/docs/_apps/distil-whisper-wrapper/v1.2/submission.json
@@ -0,0 +1,6 @@
+{
+  "time": "2024-08-08T15:48:34+00:00",
+  "submitter": "BenLambright",
+  "image": "ghcr.io/clamsproject/app-distil-whisper-wrapper:v1.2",
+  "releasenotes": "reverting back to HF pipeline using chunking transcription\n\n"
+}
diff --git a/docs/_data/app-index.json b/docs/_data/app-index.json
@@ -1,4 +1,22 @@
 {
+  "http://apps.clams.ai/distil-whisper-wrapper": {
+    "description": "The wrapper of Distil-Whisper, avaliable models: distil-large-v3, distil-large-v2, distil-medium.en, distil-small.en. The default model is distil-small.en.",
+    "latest_update": "2024-08-08T15:48:34+00:00",
+    "versions": [
+      [
+        "v1.2",
+        "BenLambright"
+      ],
+      [
+        "v1.1",
+        "keighrim"
+      ],
+      [
+        "v1.0",
+        "1192119703jzx"
+      ]
+    ]
+  },
   "http://apps.clams.ai/simple-timepoints-stitcher": {
     "description": "Stitches a sequence of `TimePoint` annotations into a sequence of `TimeFrame` annotations, performing simple smoothing of short peaks of positive labels.",
     "latest_update": "2024-08-06T12:25:05+00:00",
@@ -129,20 +147,6 @@
       ]
     ]
   },
-  "http://apps.clams.ai/distil-whisper-wrapper": {
-    "description": "The wrapper of Distil-Whisper, avaliable models: distil-large-v3, distil-large-v2, distil-medium.en, distil-small.en. The default model is distil-small.en.",
-    "latest_update": "2024-07-22T21:52:47+00:00",
-    "versions": [
-      [
-        "v1.1",
-        "keighrim"
-      ],
-      [
-        "v1.0",
-        "1192119703jzx"
-      ]
-    ]
-  },
   "http://apps.clams.ai/tfidf-keywordextractor": {
     "description": "extract keywords of a text document according to TF-IDF values. IDF values and all features come from related pickle files in the current directory.App can either take a simple text document or take a MMIF file generated from the text slicer app.",
     "latest_update": "2024-07-19T14:07:21+00:00",

diff --git a/docs/_data/apps.json b/docs/_data/apps.json