Transkript: Unterschied zwischen den Versionen

Aus bnw.bnwiki.de
Zur Navigation springen Zur Suche springen
 
(10 dazwischenliegende Versionen desselben Benutzers werden nicht angezeigt)
Zeile 1: Zeile 1:
Ein Transkript ist eine Reduzierung gesprochenen Wortes auf eine schriftliche Form. Dabei geht [[Kontext]] zum Teil verloren.
= Auto-Transcript =
= Auto-Transcript =
== Whisper ==
{{Hauptartikel|Whisper (OpenAI)}}
Steps:
# install Python 3.9.13
## setup pip (systemvariables) to go to 3.9.13
# install [https://pytorch.org/ pytorch] via pip
# install [https://github.com/openai/whisper whsiper] via pip
## pip install git+https://github.com/openai/whisper.git
https://github.com/openai/whisper/discussions/categories/show-and-tell
*To Wiki: https://www.mediawiki.org/wiki/Extension:OAuth/de
== Word ==
== Word ==
300 minuten / Monat max.
300 minuten / Monat max.
=== Word to Wiki voncert ===
=== Word to Wiki convert ===
==== Regex ====
==== Regex ====
<nowiki>Find:<br>
'''Find:'''<br><nowiki>
<br>
</nowiki><br><nowiki>
0<br>
0</nowiki><br><nowiki>
Replace:<br>
</nowiki>'''Replace:'''<br><nowiki>
<br>
</nowiki><br><nowiki>
|-<br>
|-</nowiki><br><nowiki>
| 0<br>
| 0</nowiki><br><nowiki>
Find:<br>
</nowiki>'''Find:'''<br><nowiki>
Speaker<br>
Speaker</nowiki><br><nowiki>
Replace:<br>
</nowiki>'''Replace:'''<br><nowiki>
||<br>
||</nowiki><br><nowiki>
Find:<br>
</nowiki>'''Find:'''<br><nowiki>
Transcript <br>
Transcript </nowiki><br><nowiki>
Replace:<br>
</nowiki>'''Replace:'''<br><nowiki>
{| class="wikitable"<br>
{| class="wikitable"</nowiki><br><nowiki>
|+ Transcript<br>
|+ Transcript</nowiki><br><nowiki>
|-<br>
|-</nowiki><br><nowiki>
! Timestamp !! Speaker !! Text<br>
! Timestamp !! Speaker !! Text</nowiki><br><nowiki>
Find:<br>
</nowiki>'''Find:'''<br><nowiki>
<br>
</nowiki><br><nowiki>
<br>
</nowiki><br><nowiki>
<br>
</nowiki><br><nowiki>
Replace:<br>
</nowiki>'''Replace:'''<br><nowiki>
||<br>
||</nowiki><br><nowiki>
<br>
</nowiki><br><nowiki>
Find:<br>
</nowiki>'''Find:'''<br><nowiki>
||<br>
||</nowiki><br><nowiki>
|-<br>
|-</nowiki><br><nowiki>
Replace:<br>
</nowiki>'''Replace:'''<br><nowiki>
<br>
</nowiki><br><nowiki>
|-<br>
|-</nowiki><br><nowiki>
Find:<br>
</nowiki>'''Find:'''<br><nowiki>
||<br>
||</nowiki><br><nowiki>
  <br>
  </nowiki><br><nowiki>
Replace:<br>
</nowiki>'''Replace:'''<br><nowiki>
<br>
</nowiki><br><nowiki>
|}<br>
|}</nowiki><br><nowiki>
Find(enable regex):<br>
</nowiki>'''Find(enable regex):'''<br><nowiki>
(?<=\d\d) \|\|\n<br>
(?<=\d\d) \|\|\n</nowiki><br><nowiki>
Replace:<br>
</nowiki>'''Replace:'''<br><nowiki>
  || ||<br>
  || ||</nowiki><br><nowiki>
<br>
</nowiki><br><nowiki>
Find(enable regex):<br>
</nowiki>'''Find(enable regex):'''<br><nowiki>
^Audio file \|\|$<br>
^Audio file \|\|$</nowiki><br><nowiki>
.+<br>
.+</nowiki><br><nowiki>
\|\}\|\|<br>
\|\}\|\|</nowiki><br><nowiki>
\{\|<br>
\{\|</nowiki><br><nowiki>
Replace:<br>
</nowiki>'''Replace:'''<br><nowiki>
{|<br>
{|</nowiki><br><nowiki>
#Done.</nowiki>
#Done.</nowiki>


Zeile 62: Zeile 77:
:AssemblyAI https://www.youtube.com/watch?v=rTWM5WuPhlQ
:AssemblyAI https://www.youtube.com/watch?v=rTWM5WuPhlQ
:pydub, ffmpeg and SpeechRecognition https://pythonbasics.org/transcribe-audio/
:pydub, ffmpeg and SpeechRecognition https://pythonbasics.org/transcribe-audio/
:Automatic Speech Recognition (ASR) - German https://github.com/AASHISHAG/asr-german
[[Kategorie:Idee]][[Kategorie:Tool]]
[[Kategorie:Idee]][[Kategorie:Tool]]
: Whisper https://openai.com/blog/whisper/

Aktuelle Version vom 30. Dezember 2022, 15:14 Uhr

Ein Transkript ist eine Reduzierung gesprochenen Wortes auf eine schriftliche Form. Dabei geht Kontext zum Teil verloren.

Auto-Transcript

Whisper

Steps:

  1. install Python 3.9.13
    1. setup pip (systemvariables) to go to 3.9.13
  2. install pytorch via pip
  3. install whsiper via pip
    1. pip install git+https://github.com/openai/whisper.git

https://github.com/openai/whisper/discussions/categories/show-and-tell

Word

300 minuten / Monat max.

Word to Wiki convert

Regex

Find:

0
Replace:

|-
| 0
Find:
Speaker
Replace:
||
Find:
Transcript
Replace:
{| class="wikitable"
|+ Transcript
|-
! Timestamp !! Speaker !! Text
Find:



Replace:
||

Find:
||
|-
Replace:

|-
Find:
||

Replace:

|}
Find(enable regex):
(?<=\d\d) \|\|\n
Replace:
|| ||

Find(enable regex):
^Audio file \|\|$
.+
\|\}\|\|
\{\|
Replace:
{|
#Done.

Quellen

stackoverflow: better way to automate mouse&keyboard using pyautogui[1]
Tool: pywinauto
Sleep vs tight-loop: https://stackoverflow.com/questions/34361728/windows-desktop-gui-automation-using-python-sleep-vs-tight-loop
Word-Alternativen
AssemblyAI https://www.youtube.com/watch?v=rTWM5WuPhlQ
pydub, ffmpeg and SpeechRecognition https://pythonbasics.org/transcribe-audio/
Automatic Speech Recognition (ASR) - German https://github.com/AASHISHAG/asr-german
Whisper https://openai.com/blog/whisper/
  1. ↑ stackoverflow: better way to automate mouse&keyboard using pyautogui https://stackoverflow.com/questions/42412157/better-way-to-automate-mousekeyboard-using-pyautogui
Abgerufen von „https://bnw.bnwiki.de/index.php?title=Transkript&oldid=1346“