I Installed Kdenlive on my Windows 10 PC. I added two language packs. It said I needed pip3 to use the speech to text transcription. I found info about pip3 here: https://www.activestate.com/resources/q ... -use-pip3/ I used this info to install pip3.
That was not enough so then I used the internal menu of Kdenlive to install a full? python package.

When I try to use speech to text I get:
Traceback (most recent call last):
File "C:/Users/Media Dude/AppData/Local/kdenlive/bin/data/kdenlive/scripts/speechtotext.py", line 29, in <module>
model = Model(sys.argv[2])
File "C:\Users\Media Dude\AppData\Local\Programs\Python\Python36-32\lib\site-packages\vosk\__init__.py", line 53, in __init__
raise Exception("Failed to create a model")
Exception: Failed to create a model

I know nothing about Python and I don't really want to know. I just want to get the speech to text to work.

Maybe I should uninstall both python and kdenlive and start again.

Kdenlive installed under users. Is it OK to install under Program Files?
Should I install the Python package first, before Kdenlive?
Can you point to a install Python for dummies guide?

Kdenlive uses Vosk models through a module written in Python.

I found the place in the Python module code where the error occurred: https://github.com/alphacep/vosk-api/bl ... t__.py#L53

Depending on where the error occurred, the Vosk module itself is installed and connected. It is possible that the models for your language could not be loaded. The website of the Vosk module developer has examples on how to check if the installation is correct:

Code: Select all

vosk-transcriber -i test.mp4 -o test.txt
vosk-transcriber -l fr -i test.m4a -t srt -o test.srt
vosk-transcriber --list-languages


Please, see https://alphacephei.com/vosk/install

Should I install the Python package first, before Kdenlive?

I see no problem installing Python itself. The problem is somewhere beyond that.