Added: vosk functionality

controllers/default.py

@@ -4,59 +4,21 @@
 # this file is released under public domain and you can use without limitations
 # -------------------------------------------------------------------------
 
+#from transcription_tools import create_vtt
+transcription_tools = local_import('transcription_tools', reload=True)
+
 # ---- example index page ----
 def index():
-    images = db().select(db.image.ALL, orderby=db.image.title)
+    media_files = db().select(db.media_file.ALL, orderby=db.media_file.title)
-    return dict(images=images)
+    return dict(media_files=media_files)
 
+@auth.requires_membership('manager')
 def manage():   
-    grid = SQLFORM.smartgrid(db.image, linked_tables=['post'])
+    grid = SQLFORM.smartgrid(db.media_file, linked_tables=['post'])
     return dict(grid=grid)
 
-# ---- API (example) -----
+def vtt():
-@auth.requires_login()
+    return dict(message=transcription_tools.create_vtt())
-def api_get_user_email():
-    if not request.env.request_method == 'GET': raise HTTP(403)
-    return response.json({'status':'success', 'email':auth.user.email})
 
-# ---- Smart Grid (example) -----
-@auth.requires_membership('admin') # can only be accessed by members of admin groupd
-def grid():
-    response.view = 'generic.html' # use a generic view
-    tablename = request.args(0)
-    if not tablename in db.tables: raise HTTP(403)
-    grid = SQLFORM.smartgrid(db[tablename], args=[tablename], deletable=False, editable=False)
-    return dict(grid=grid)
-
-# ---- Embedded wiki (example) ----
-def wiki():
-    auth.wikimenu() # add the wiki to the menu
-    return auth.wiki() 
-
-# ---- Action for login/register/etc (required for auth) -----
 def user():
-    """
-    exposes:
-    http://..../[app]/default/user/login
-    http://..../[app]/default/user/logout
-    http://..../[app]/default/user/register
-    http://..../[app]/default/user/profile
-    http://..../[app]/default/user/retrieve_password
-    http://..../[app]/default/user/change_password
-    http://..../[app]/default/user/bulk_register
-    use @auth.requires_login()
-        @auth.requires_membership('group name')
-        @auth.requires_permission('read','table name',record_id)
-    to decorate functions that need access control
-    also notice there is http://..../[app]/appadmin/manage/auth to allow administrator to manage users
-    """
     return dict(form=auth())
-
-# ---- action to server uploaded static content (required) ---
-@cache.action()
-def download():
-    """
-    allows downloading of uploaded files
-    http://..../[app]/default/download/[filename]
-    """
-    return response.download(request, db)

languages/de.py

@@ -1,8 +1,10 @@
 # -*- coding: utf-8 -*-
 {
+'!=': '!=',
 '!langcode!': 'de',
 '!langname!': 'Deutsch (DE)',
 '"update" is an optional expression like "field1=\'newvalue\'". You cannot update or delete the results of a JOIN': '"Update" ist ein optionaler Ausdruck wie "feld1=\'newvalue\'". JOIN Ergebnisse können nicht aktualisiert oder gelöscht werden',
+'%(nrows)s records found': '%(nrows)s records found',
 '%s %%{row} deleted': '%s %%{row} gelöscht',
 '%s %%{row} updated': '%s %%{row} aktualisiert',
 '%s selected': '%s ausgewählt',
@@ -12,6 +14,13 @@
 '**%(items)s** %%{item(items)}, **%(bytes)s** %%{byte(bytes)}': '**%(items)s** %%{Item(Items)}, **%(bytes)s** %%{Byte(Bytes)}',
 '**%(items)s** items, **%(bytes)s** %%{byte(bytes)}': '**%(items)s** Items, **%(bytes)s** %%{Byte(Bytes)}',
 '**not available** (requires the Python [[guppy http://pypi.python.org/pypi/guppy/ popup]] library)': '**nicht verfügbar** (benötigt die Python [[guppy http://pypi.python.org/pypi/guppy/ popup]] Bibliothek)',
+'+ And': '+ And',
+'+ Or': '+ Or',
+'<': '<',
+'<=': '<=',
+'=': '=',
+'>': '>',
+'>=': '>=',
 '?': '?',
 '@markmin\x01(**%.0d MB**)': '(**%.0d\xa0MB**)',
 '@markmin\x01**%(items)s** %%{item(items)}, **%(bytes)s** %%{byte(bytes)}': '**%(items)s** %%{Item(items)}, **%(bytes)s** %%{Byte(bytes)}',
@@ -28,6 +37,10 @@
 'A new password was emailed to you': 'Ein neues Passwort wurde per E-Mail an Sie gesendet',
 'About': 'Über',
 'Access Control': 'Zugangskontrolle',
+'Add Record': 'Add Record',
+'Add record to database': 'Add record to database',
+'Add this to the search as an AND term': 'Add this to the search as an AND term',
+'Add this to the search as an OR term': 'Add this to the search as an OR term',
 'admin': 'admin',
 'Ajax Recipes': 'Ajax Rezepte',
 'An error occured, please [[reload %s]] the page': 'Ein Fehler ist aufgetreten, bitte [[laden %s]] Sie die Seite neu',
@@ -37,6 +50,7 @@
 'Are you sure you want to delete this object?': 'Sind Sie sich sicher, dass Sie dieses Objekt löschen wollen?',
 'Authentication code': 'Authentifizierungs code',
 'Available Databases and Tables': 'Verfügbare Datenbanken und Tabellen',
+'Back': 'Back',
 "Buy web2py's book": "web2py's Buch kaufen",
 'Cache': 'Zwischenspeicher',
 'cache': 'zwischenspeicher',
@@ -44,20 +58,27 @@
 'Cache contains items up to **%(hours)02d** %%{hour(hours)} **%(min)02d** %%{minute(min)} **%(sec)02d** %%{second(sec)} old.': 'Cache enthält items die bis zu **%(hours)02d** %%{hour(hours)} **%(min)02d** %%{minute(min)} **%(sec)02d** %%{second(sec)} alt sind.',
 'Cache Keys': 'Cache Schlüssel',
 'Cannot be empty': 'Darf nicht leer sein',
-'Change Password': 'Canviï la Contrasenya',
+'Change Password': 'Passwort ändern',
 'Change password': 'Canviï la contrasenya',
 'Check to delete': 'Auswählen um zu löschen',
+'Clear': 'Clear',
 'Clear CACHE?': 'CACHE löschen?',
 'Clear DISK': 'DISK löschen',
 'Clear RAM': 'RAM löschen',
 'Click on the link %(link)s to reset your password': 'Klicke auf den Link %(link)s um das Passwort zurückzusetzen',
 'Client IP': 'Client IP',
+'Close': 'Close',
+'Comma-separated export including columns not shown; fields from other tables are exported as raw values for faster export': 'Comma-separated export including columns not shown; fields from other tables are exported as raw values for faster export',
+'Comma-separated export of visible columns. Fields from other tables are exported as they appear on-screen but this may be slow for many rows': 'Comma-separated export of visible columns. Fields from other tables are exported as they appear on-screen but this may be slow for many rows',
 'Community': 'Community',
 'Components and Plugins': 'Komponenten und Plugins',
 'Config.ini': 'Config.ini',
 'Confirm Password': 'Passwort bestätigen',
+'contains': 'contains',
 'Controller': 'Controller',
 'Copyright': 'Urheberrechte',
+'CSV': 'CSV',
+'CSV (hidden cols)': 'CSV (hidden cols)',
 'Current request': 'Derzeitiger Request',
 'Current response': 'Derzeitige Response',
 'Current session': 'Derzeitige Session',
@@ -67,6 +88,7 @@
 'Database Administration (appadmin)': 'Datenbankadministration (appadmin)',
 'db': 'db',
 'DB Model': 'Muster-DB',
+'Delete': 'Delete',
 'Delete:': 'Lösche:',
 'Demo': 'Demo',
 'Deployment Recipes': 'Entwicklungsrezepte',
@@ -82,6 +104,8 @@
 'done!': 'Fertig!',
 'Download': 'Download',
 'E-mail': 'Email',
+'Edit': 'Edit',
+'Edit %(entity)s': 'Edit %(entity)s',
 'Edit current record': 'Diesen Eintrag editieren',
 'Email and SMS': 'Email und SMS',
 'Email sent': 'Email gesendet',
@@ -89,7 +113,11 @@
 'Email verified': 'Email-Verifiziert',
 'Errors': 'Fehlermeldungen',
 'export as csv file': 'als csv Datei exportieren',
+'Export:': 'Export:',
 'FAQ': 'FAQ',
+'file': 'file',
+'file ## download': 'file ',
+'File Filename': 'File Filename',
 'First name': 'Vorname',
 'Forms and Validators': 'Forms und Validators',
 'Free Applications': 'Kostenlose Anwendungen',
@@ -98,7 +126,7 @@
 'Grid Example': 'Rasterbeispiel',
 'Group %(group_id)s created': 'Grupo %(group_id)s creat',
 'Group %(group_id)s deleted': 'Gruppe %(group_id)s gelöscht',
-'Group ID': 'ID de Grup',
+'Group ID': 'ID Benutzergruppe',
 'Group uniquely assigned to user %(id)s': 'Gruppe eindeutig dem Benutzer zugewiesen %(id)s',
 'Groups': 'Gruppen',
 'Hello World': 'Hallo Welt',
@@ -106,10 +134,15 @@
 'Hit Ratio: **%(ratio)s%%** (**%(hits)s** %%{hit(hits)} and **%(misses)s** %%{miss(misses)})': 'Trefferquote: **%(ratio)s%%** (**%(hits)s** %%{hit(hits)} und **%(misses)s** %%{miss(misses)})',
 'Home': 'Startseite',
 'How did you get here?': 'Wie sind Sie hier her gelangt?',
+'HTML': 'HTML',
+'HTML export of visible columns': 'HTML export of visible columns',
+'Id': 'Id',
+'Images': 'Images',
 'import': 'Importieren',
 'Import/Export': 'Importieren/Exportieren',
+'in': 'in',
 'Incorrect code. {0} more attempt(s) remaining.': 'Falscher Code. {0} weitere Versuche verbleiben.',
-'Insufficient privileges': 'Privilegis insuficients',
+'Insufficient privileges': 'Unzureichende Berechtigungen',
 'Internal State': 'Innerer Zustand',
 'Introduction': 'Einführung',
 'Invalid email': 'Ungültige Email',
@@ -122,6 +155,8 @@
 'Invalid user': 'Ungültiger Benutzer',
 'Invalid username': 'Ungültiger Benutzername',
 'Invitation to join %(site)s': 'Einladung um %(site)s zujoinen',
+'JSON': 'JSON',
+'JSON export of visible columns': 'JSON export of visible columns',
 'Key': 'Schlüssel',
 'Key verified': 'Schlüssel verifiziert',
 'Last name': 'Nachname',
@@ -138,15 +173,22 @@
 'Manage %(action)s': '%(action)s verwalten',
 'Manage Access Control': 'Zugangskontrolle verwalten',
 'Manage Cache': 'Cache verwalten',
+'Media files': 'Media files',
 'Memberships': 'Mitgliedschaften',
 'Menu Model': 'Menü-Muster',
+'Movies': 'Movies',
 'My Sites': 'Meine Seiten',
 'Name': 'Nombre',
+'New %(entity)s': 'New %(entity)s',
 'New password': 'Contrasenya nova',
 'New Record': 'Neuer Eintrag',
 'new record inserted': 'Neuer Eintrag hinzugefügt',
+'New Search': 'New Search',
 'next %s rows': 'nächste %s Reihen',
 'No databases in this application': 'Keine Datenbank in dieser Anwendung',
+'No records found': 'No records found',
+'Not Authorized': 'Zugriff verweigert',
+'not in': 'not in',
 'Number of entries: **%s**': 'Nummer der Einträge: **%s**',
 'Object or table name': 'Objekt oder Tabellenname',
 'Old password': 'Altes Passwort',
@@ -165,10 +207,11 @@
 'Permissions': 'Erlaubnisse',
 'please input your password again': 'si us plau, entri un altre cop la seva contrasenya',
 'Plugins': 'Plugins',
+'Posts': 'Posts',
 'Powered by': 'Unterstützt von',
 'Preface': 'Allgemeines',
 'previous %s rows': 'vorherige %s Reihen',
-'Profile': 'Perfil',
+'Profile': 'Profil',
 'Profile updated': 'Profil aktualisiert',
 'pygraphviz library not found': 'pygraphviz Bibliothek wurde nicht gefunden',
 'Python': 'Python',
@@ -205,10 +248,15 @@
 'Rows in Table': 'Tabellenreihen',
 'Rows selected': 'Reihen ausgewählt',
 'Save model as...': 'Speichere Vorlage als...',
+'Search': 'Search',
 'Services': 'Dienste',
 'Sign Up': 'Registrieren',
 'Sign up': 'Registrieren',
 'Size of cache:': 'Cachegröße:',
+'Spreadsheet-optimised export of tab-separated content including hidden columns. May be slow': 'Spreadsheet-optimised export of tab-separated content including hidden columns. May be slow',
+'Spreadsheet-optimised export of tab-separated content, visible columns only. May be slow.': 'Spreadsheet-optimised export of tab-separated content, visible columns only. May be slow.',
+'Start building a new search': 'Start building a new search',
+'starts with': 'starts with',
 'state': 'Status',
 'Statistics': 'Statistik',
 'Stylesheet': 'Stylesheet',
@@ -225,7 +273,10 @@
 'This email already has an account': 'Zu dieser Email gehört bereits ein Account',
 'Time in Cache (h:m:s)': 'Zeit im Cache (h:m:s)',
 'Timestamp': 'Zeitstempel',
+'Title': 'Title',
 'Traceback': 'Zurückverfolgen',
+'TSV (Spreadsheets)': 'TSV (Spreadsheets)',
+'TSV (Spreadsheets, hidden cols)': 'TSV (Spreadsheets, hidden cols)',
 'Twitter': 'Twitter',
 'Two-step Login Authentication Code': 'Zweistufiger Login-Authentifizierungscode',
 'unable to parse csv file': 'csv Datei konnte nicht geparst werden',
@@ -244,19 +295,24 @@
 'User %(id)s Username retrieved': 'Se ha recuperat el nom de usuari del usuari %(id)s',
 'User %(id)s Verification email sent': 'Benutzer %(id)s Bestätigungs-Email gesendet',
 'User %(id)s verified registration key': 'Benutzer %(id)s verifizierter Registrierungsschlüssel',
-'User ID': 'ID de Usuari',
+'User ID': 'ID des Benutzers',
 'Username': 'Benutzername',
 'Username already taken': 'Benutzername schon vergeben',
 'Username retrieve': 'Recuperar nom de usuari',
 'Users': 'Benutzer',
+'Value already in database or empty': 'Value already in database or empty',
 'Verify Password': 'Verificar Contrasenya',
 'Videos': 'Videos',
 'View': 'Ansicht',
+'View %(entity)s': 'View %(entity)s',
+'Vtt Url': 'Vtt Url',
 'Welcome %(username)s! Click on the link %(link)s to verify your email': 'Willkommen %(username)s! Klicken Sie auf den Link %(link)s, um Ihre Email zu bestätigen',
 'Welcome to web2py!': 'Willkommen bei web2py!',
 'Which called the function %s located in the file %s': 'Welche die Funktion %s in der Datei %s aufrief',
 'Wiki Example': 'Wiki Beispiel',
 'Working...': 'Arbeite...',
+'XML': 'XML',
+'XML export of columns shown': 'XML export of columns shown',
 'You are successfully running web2py': 'web2py wird erfolgreich ausgeführt',
 'You can modify this application and adapt it to your needs': 'Sie können diese Anwendung verändern und Ihren Bedürfnissen anpassen',
 'You have been invited to join %(site)s, click %(link)s to complete the process': 'Sie wurden eingeladen,%(site)s beizutreten. Klicken Sie auf %(link)s, um den Vorgang abzuschließen',

models/db.py

@@ -155,21 +155,11 @@ if configuration.get('scheduler.enabled'):
 # auth.enable_record_versioning(db)
 db = DAL("sqlite://storage.sqlite")
 
-db.define_table('image',
+db.define_table('media_file',
                 Field('title', unique=True),
-                Field('file', 'upload'),
+                Field('vtt_url'),
+                Field('file', 'upload', autodelete=True),
                 format = '%(title)s')
 
-db.define_table('post',
+auth = Auth(db)
-                Field('image_id', 'reference image'),
+auth.define_tables(username=True)
-                Field('author'),
-                Field('email'),
-                Field('body', 'text'))
-
-db.image.title.requires = IS_NOT_IN_DB(db, db.image.title)
-db.post.image_id.requires = IS_IN_DB(db, db.image.id, '%(title)s')
-db.post.author.requires = IS_NOT_EMPTY()
-db.post.email.requires = IS_EMAIL()
-db.post.body.requires = IS_NOT_EMPTY()
-
-db.post.image_id.writable = db.post.image_id.readable = False

modules/.gitignore

@@ -0,0 +1,13 @@
+/_cffi_backend.cpython-36m-x86_64-linux-gnu.so
+/bin/
+/cffi-1.14.6.dist-info/
+/cffi.libs/
+/cffi/
+/pycparser-2.20.dist-info/
+/pycparser/
+/srt-3.5.0.dist-info/
+/srt.py
+/srt_tools/
+/vosk/
+/vosk-0.3.31.dist-info/
+/vosk.libs/

modules/transcription_tools/__init__.py

@@ -0,0 +1,50 @@
+from vosk import Model, KaldiRecognizer, SetLogLevel
+import sys
+import os
+import wave
+import subprocess
+import srt
+import json
+import datetime
+
+
+def create_vtt():
+    sample_rate = 16000
+    model = Model("applications/transcription/private/model")
+    rec = KaldiRecognizer(model, sample_rate)
+    rec.SetWords(True)
+
+    process = subprocess.Popen(['ffmpeg', '-loglevel', 'quiet', '-i',
+                                '/home/mschmidt/Videos/100-Meinungen-Video-erstellen.mp4',
+                                '-ar', str(sample_rate) , '-ac', '1', '-f', 's16le', '-'],
+                                stdout=subprocess.PIPE)
+
+    WORDS_PER_LINE = 7
+
+    def transcribe():
+        results = []
+        subs = []
+        while True:
+            data = process.stdout.read(4000)
+            if len(data) == 0:
+                break
+            if rec.AcceptWaveform(data):
+                results.append(rec.Result())
+        results.append(rec.FinalResult())
+
+        for i, res in enumerate(results):
+            jres = json.loads(res)
+            if not 'result' in jres:
+                continue
+            words = jres['result']
+            for j in range(0, len(words), WORDS_PER_LINE):
+                line = words[j : j + WORDS_PER_LINE] 
+                s = srt.Subtitle(index=len(subs), 
+                    content=" ".join([l['word'] for l in line]),
+                    start=datetime.timedelta(seconds=line[0]['start']), 
+                    end=datetime.timedelta(seconds=line[-1]['end']))
+                subs.append(s)
+        return subs
+
+    return (srt.compose(transcribe()))
+

private/.gitignore

@@ -0,0 +1 @@
+/model/

views/default/index.html

@@ -2,10 +2,10 @@
 
 <div class="row">
   <div class="col-md-12">
-<h1>Current Images</h1>
+<h1>Mediendateien</h1>
 <ul>
-{{for image in images:}}
+{{for media_file in media_files:}}
-{{=LI(A(image.title, _href=URL("show", args=image.id)))}}
+{{=LI(A(media_file.title, _href=URL("show", args=media_file.id)))}}
 {{pass}}
 </ul>
   </div>

views/default/vtt.html

@@ -0,0 +1,8 @@
+{{extend 'layout.html'}}
+<div class="row">
+	<div class="col-md-12">
+	
+		<p>{{=message}}</p>
+	
+	</div>
+</div>