PR comments

client/src/app/+admin/overview/videos/video-list.component.ts

@@ -1,7 +1,7 @@
 import { DatePipe, NgClass, NgFor, NgIf } from '@angular/common'
 import { Component, OnInit, ViewChild } from '@angular/core'
 import { ActivatedRoute, Router, RouterLink } from '@angular/router'
-import { AuthService, ConfirmService, Notifier, RestPagination, RestTable } from '@app/core'
+import { AuthService, ConfirmService, Notifier, RestPagination, RestTable, ServerService } from '@app/core'
 import { formatICU, getAbsoluteAPIUrl } from '@app/helpers'
 import { Video } from '@app/shared/shared-main/video/video.model'
 import { VideoService } from '@app/shared/shared-main/video/video.service'
@@ -27,6 +27,7 @@ import {
   VideoActionsDropdownComponent
 } from '../../../shared/shared-video-miniature/video-actions-dropdown.component'
 import { VideoAdminService } from './video-admin.service'
+import { VideoCaptionService } from '@app/shared/shared-main/video-caption/video-caption.service'
 
 @Component({
   selector: 'my-video-list',
@@ -81,7 +82,8 @@ export class VideoListComponent extends RestTable <Video> implements OnInit {
     removeFiles: true,
     transcoding: true,
     studio: true,
-    stats: true
+    stats: true,
+    generateTranscription: true
   }
 
   loading = true
@@ -94,7 +96,9 @@ export class VideoListComponent extends RestTable <Video> implements OnInit {
     private notifier: Notifier,
     private videoService: VideoService,
     private videoAdminService: VideoAdminService,
-    private videoBlockService: VideoBlockService
+    private videoBlockService: VideoBlockService,
+    private videoCaptionService: VideoCaptionService,
+    private server: ServerService
   ) {
     super()
   }
@@ -103,6 +107,10 @@ export class VideoListComponent extends RestTable <Video> implements OnInit {
     return this.auth.getUser()
   }
 
+  get serverConfig () {
+    return this.server.getHTMLConfig()
+  }
+
   ngOnInit () {
     this.initialize()
 
@@ -154,6 +162,14 @@ export class VideoListComponent extends RestTable <Video> implements OnInit {
           isDisplayed: videos => videos.every(v => v.canRemoveFiles(this.authUser)),
           iconName: 'delete'
         }
+      ],
+      [
+        {
+          label: $localize`Generate caption`,
+          handler: videos => this.generateCaption(videos),
+          isDisplayed: videos => videos.every(v => v.canGenerateTranscription(this.authUser, this.serverConfig.videoTranscription.enabled)),
+          iconName: 'video-lang'
+        }
       ]
     ]
   }
@@ -371,4 +387,15 @@ export class VideoListComponent extends RestTable <Video> implements OnInit {
         error: err => this.notifier.error(err.message)
       })
   }
+
+  private generateCaption (videos: Video[]) {
+    this.videoCaptionService.generateCaption(videos.map(v => v.id))
+      .subscribe({
+        next: () => {
+          this.notifier.success($localize`Transcription jobs created.`)
+        },
+
+        error: err => this.notifier.error(err.message)
+      })
+  }
 }

client/src/app/shared/shared-main/buttons/action-dropdown.component.scss

@@ -63,6 +63,10 @@
 
     &.with-icon {
       @include dropdown-with-icon-item;
+
+      .icon-video-lang {
+        top: 0;
+      }
     }
 
     a,

client/src/app/shared/shared-main/video-caption/video-caption.service.ts

@@ -1,15 +1,15 @@
-import { Observable, of } from 'rxjs'
-import { catchError, map, switchMap } from 'rxjs/operators'
 import { HttpClient } from '@angular/common/http'
 import { Injectable } from '@angular/core'
 import { RestExtractor, ServerService } from '@app/core'
 import { objectToFormData } from '@app/helpers'
 import { peertubeTranslate, sortBy } from '@peertube/peertube-core-utils'
 import { ResultList, VideoCaption } from '@peertube/peertube-models'
+import { Observable, from, of } from 'rxjs'
+import { catchError, concatMap, map, switchMap, toArray } from 'rxjs/operators'
 import { environment } from '../../../../environments/environment'
-import { VideoCaptionEdit } from './video-caption-edit.model'
 import { VideoPasswordService } from '../video/video-password.service'
 import { VideoService } from '../video/video.service'
+import { VideoCaptionEdit } from './video-caption-edit.model'
 
 @Injectable()
 export class VideoCaptionService {
@@ -74,4 +74,13 @@ export class VideoCaptionService {
   getCaptionContent ({ captionPath }: Pick<VideoCaption, 'captionPath'>) {
     return this.authHttp.get(environment.originServerUrl + captionPath, { responseType: 'text' })
   }
+
+  generateCaption (videoIds: (number | string)[]) {
+    return from(videoIds)
+      .pipe(
+        concatMap(videoId => this.authHttp.post(`${VideoService.BASE_VIDEO_URL}/${videoId}/captions/generate`, {})),
+        toArray(),
+        catchError(err => this.restExtractor.handleError(err))
+      )
+  }
 }

client/src/app/shared/shared-main/video/video.model.ts

@@ -244,6 +244,10 @@ export class Video implements VideoServerModel {
       this.isUpdatableBy(user)
   }
 
+  canGenerateTranscription (user: AuthUser, transcriptionEnabled: boolean) {
+    return transcriptionEnabled && this.isLocal && user.hasRight(UserRight.UPDATE_ANY_VIDEO)
+  }
+
   // ---------------------------------------------------------------------------
 
   isOwner (user: AuthUser) {

client/src/app/shared/shared-video-miniature/video-actions-dropdown.component.ts

@@ -11,6 +11,7 @@ import {
   DropdownButtonSize,
   DropdownDirection
 } from '../shared-main/buttons/action-dropdown.component'
+import { VideoCaptionService } from '../shared-main/video-caption/video-caption.service'
 import { RedundancyService } from '../shared-main/video/redundancy.service'
 import { VideoDetails } from '../shared-main/video/video-details.model'
 import { Video } from '../shared-main/video/video.model'
@@ -37,6 +38,7 @@ export type VideoActionsDisplayType = {
   transcoding?: boolean
   studio?: boolean
   stats?: boolean
+  generateTranscription?: boolean
 }
 
 @Component({
@@ -115,6 +117,7 @@ export class VideoActionsDropdownComponent implements OnChanges {
     private videoBlocklistService: VideoBlockService,
     private screenService: ScreenService,
     private videoService: VideoService,
+    private videoCaptionService: VideoCaptionService,
     private redundancyService: RedundancyService,
     private serverService: ServerService
   ) { }
@@ -206,6 +209,10 @@ export class VideoActionsDropdownComponent implements OnChanges {
     return this.video.isLiveInfoAvailableBy(this.user)
   }
 
+  canGenerateTranscription () {
+    return this.video.canGenerateTranscription(this.user, this.serverService.getHTMLConfig().videoTranscription.enabled)
+  }
+
   isVideoDownloadableByAnonymous () {
     return (
       this.video &&
@@ -338,14 +345,25 @@ export class VideoActionsDropdownComponent implements OnChanges {
     this.videoService.runTranscoding({ videos: [ video ], type, askForForceTranscodingIfNeeded: true })
       .subscribe({
         next: () => {
-          this.notifier.success($localize`Transcoding jobs created for "${video.name}".`)
+          this.notifier.success($localize`Transcoding job created for "${video.name}".`)
           this.transcodingCreated.emit()
         },
 
         error: err => this.notifier.error(err.message)
       })
   }
 
+  generateCaption (video: Video) {
+    this.videoCaptionService.generateCaption([ video.id ])
+      .subscribe({
+        next: () => {
+          this.notifier.success($localize`Transcription job created for "${video.name}".`)
+        },
+
+        error: err => this.notifier.error(err.message)
+      })
+  }
+
   onVideoBlocked () {
     this.videoBlocked.emit()
   }
@@ -466,6 +484,14 @@ export class VideoActionsDropdownComponent implements OnChanges {
           iconName: 'delete'
         }
       ],
+      [
+        {
+          label: $localize`Generate caption`,
+          handler: ({ video }) => this.generateCaption(video),
+          isDisplayed: () => this.displayOptions.generateTranscription && this.canGenerateTranscription(),
+          iconName: 'video-lang'
+        }
+      ],
       [ // actions regarding the account/its server
         {
           label: $localize`Mute account`,

packages/tests/package.json

@@ -6,7 +6,8 @@
   "devDependencies": {},
   "scripts": {
     "build": "tsc",
-    "watch": "tsc -w"
+    "watch": "tsc -w",
+    "install-dependencies:transcription": "pip install -r ./requirements.txt ../transcription-devtools/requirements.txt"
   },
   "dependencies": {}
 }

packages/tests/requirements.txt

@@ -0,0 +1,2 @@
+whisper-ctranslate2
+openai-whisper

packages/tests/src/transcription/whisper/openai-transcriber.spec.ts

@@ -33,7 +33,7 @@ describe('Open AI Whisper transcriber', function () {
     engine: {
       name: 'openai-whisper',
       type: 'binary',
-      binary: 'whisper',
+      command: 'whisper',
       supportedModelFormats: [ 'PyTorch' ],
       languageDetection: true,
       version: ''

packages/tests/src/transcription/whisper/whisper-ctranslate2.spec.ts

@@ -27,7 +27,7 @@ describe('Whisper CTranslate2 transcriber', function () {
     engine: {
       name: 'whisper-ctranslate2',
       type: 'binary',
-      binary: 'whisper-ctranslate2',
+      command: 'whisper-ctranslate2',
       supportedModelFormats: [ 'CTranslate2' ],
       languageDetection: true,
       version: '0.4.4'
@@ -152,7 +152,7 @@ describe('Whisper CTranslate2 transcriber', function () {
       engine: {
         name: 'openai-whisper',
         type: 'binary',
-        binary: 'whisper',
+        command: 'whisper',
         supportedModelFormats: [ 'PyTorch' ],
         version: '0.4.4'
       },

packages/transcription-devtools/requirements.txt

@@ -0,0 +1 @@
+jiwer

packages/transcription-devtools/src/benchmark.ts

@@ -122,7 +122,7 @@ void (async () => {
 
       benchmarkResults = benchmarkReducer(benchmarkResults, {
         uuid,
-        engine: transcriber.getEngine(),
+        engine: transcriber.engine,
         WER: await evaluator.wer(),
         CER: await evaluator.cer(),
         model: model.name

packages/transcription/README.md

@@ -33,7 +33,7 @@ import { OpenaiTranscriber } from '@peertube/peertube-transcription'
   // Create a transcriber powered by OpenAI Whisper CLI
   const transcriber = new OpenaiTranscriber({
     name: 'openai-whisper',
-    binary: 'whisper',
+    command: 'whisper',
     languageDetection: true,
     binDirectory
   });

packages/transcription/src/abstract-transcriber.ts

@@ -18,7 +18,8 @@ export interface TranscribeArgs {
 }
 
 export abstract class AbstractTranscriber {
-  protected engine: TranscriptionEngine
+  engine: TranscriptionEngine
+
   protected binDirectory: string
   protected enginePath: string
 
@@ -67,25 +68,14 @@ export abstract class AbstractTranscriber {
     return model.format === 'PyTorch'
   }
 
-  getEngine () {
-    return this.engine
-  }
-
   protected getEngineBinary () {
     if (this.enginePath) return this.enginePath
-    if (this.binDirectory) return join(this.binDirectory, this.engine.binary)
+    if (this.binDirectory) return join(this.binDirectory, this.engine.command)
 
-    return this.engine.binary
+    return this.engine.command
   }
 
-  abstract transcribe ({
-    mediaFilePath,
-    model,
-    language,
-    format = 'vtt',
-    transcriptDirectory,
-    runId = buildSUUID()
-  }: TranscribeArgs): Promise<TranscriptFile>
+  abstract transcribe (options: TranscribeArgs): Promise<TranscriptFile>
 
   abstract install (path: string): Promise<void>
 }

packages/transcription/src/transcription-engine.ts

@@ -7,7 +7,7 @@ export interface TranscriptionEngine {
   description?: string
   language?: string
   type: 'binary'
-  binary: string
+  command: string
   version: string
   license?: string
   forgeURL?: string

packages/transcription/src/whisper/engines.ts

@@ -6,7 +6,7 @@ export const engines: TranscriptionEngine[] = [
     description: 'High-performance inference of OpenAI\'s Whisper automatic speech recognition model',
     language: 'python',
     type: 'binary',
-    binary: 'whisper',
+    command: 'whisper',
     forgeURL: 'https://github.com/openai/whisper',
     license: 'MIT',
     supportedModelFormats: [ 'PyTorch' ],
@@ -18,7 +18,7 @@ export const engines: TranscriptionEngine[] = [
     description: 'Whisper command line client compatible with original OpenAI client based on CTranslate2.',
     language: 'python',
     type: 'binary',
-    binary: 'whisper-ctranslate2',
+    command: 'whisper-ctranslate2',
     forgeURL: 'https://github.com/Softcatala/whisper-ctranslate2',
     license: 'MIT',
     supportedModelFormats: [ 'CTranslate2' ],

scripts/ci.sh

@@ -131,7 +131,7 @@ elif [ "$1" = "api-5" ]; then
 
     MOCHA_PARALLEL=true runJSTest "$1" $((2*$speedFactor)) $transcodingFiles $runnersFiles
 elif [ "$1" = "external-plugins" ]; then
-    pip install whisper-ctranslate2 openai-whisper jiwer
+    npm run install-dependencies:transcription --workspace=@peertube/tests
 
     npm run build:server
     npm run build:tests
@@ -149,7 +149,7 @@ elif [ "$1" = "lint" ]; then
 
     ( cd client && npm run lint )
 elif [ "$1" = "transcription" ]; then
-    pip install whisper-ctranslate2 openai-whisper jiwer
+    npm run install-dependencies:transcription --workspace=@peertube/tests
 
     npm run build:server
     npm run build:tests

server/core/lib/video-captions.ts

@@ -84,7 +84,7 @@ export async function generateSubtitle (options: {
       })
 
       if (!CONFIG.VIDEO_TRANSCRIPTION.ENGINE_PATH) {
-        logger.info(`Installing transcriber ${transcriber.getEngine().name} to generate subtitles`, lTags())
+        logger.info(`Installing transcriber ${transcriber.engine.name} to generate subtitles`, lTags())
         await transcriber.install(DIRECTORIES.LOCAL_PIP_DIRECTORY)
       }
     }

support/doc/development/tests.md

@@ -46,7 +46,7 @@ jiwer --help
 Otherwise, install the packages. On Debian-based systems (like Debian, Ubuntu or Mint):
 ```bash
 sudo apt-get install parallel libimage-exiftool-perl
-sudo pip install whisper-ctranslate2 openai-whisper
+sudo pip install -r packages/tests/requirements.txt -r packages/transcription-devtools/requirements.txt
 ```
 
 ### Test