h3ll3
commented
11 months ago Okay - some more Infos i found out:
... .vtt file and .srt file are existent at uploaded videos, not at recorded live streams. isn't it possible to autocreate subtitles at recorded and hls encoded livestreams?
I can check CC option when watching the video on both types.
at recorded live streams, i can only find .srt.log file which contains
LOG (VoskAPI:ReadDataFiles():model.cc:213) Decoding params beam=13 max-active=7000 lattice-beam=6
LOG (VoskAPI:ReadDataFiles():model.cc:216) Silence phones 1:2:3:4:5:6:7:8:9:10
LOG (VoskAPI:RemoveOrphanNodes():nnet-nnet.cc:948) Removed 0 orphan nodes.
LOG (VoskAPI:RemoveOrphanComponents():nnet-nnet.cc:847) Removing 0 orphan components.
LOG (VoskAPI:ReadDataFiles():model.cc:248) Loading i-vector extractor from /usr/share/vosk/vosk-model-de-0.21/ivector/final.ie
LOG (VoskAPI:ComputeDerivedVars():ivector-extractor.cc:183) Computing derived variables for iVector extractor
LOG (VoskAPI:ComputeDerivedVars():ivector-extractor.cc:204) Done.
LOG (VoskAPI:ReadDataFiles():model.cc:279) Loading HCLG from /usr/share/vosk/vosk-model-de-0.21/graph/HCLG.fst
LOG (VoskAPI:ReadDataFiles():model.cc:297) Loading words from /usr/share/vosk/vosk-model-de-0.21/graph/words.txt
LOG (VoskAPI:ReadDataFiles():model.cc:308) Loading winfo /usr/share/vosk/vosk-model-de-0.21/graph/phones/word_boundary.int
LOG (VoskAPI:ReadDataFiles():model.cc:315) Loading subtract G.fst model from /usr/share/vosk/vosk-model-de-0.21/rescore/G.fst
LOG (VoskAPI:ReadDataFiles():model.cc:317) Loading CARPA model from /usr/share/vosk/vosk-model-de-0.21/rescore/G.carpa
LOG (VoskAPI:ReadDataFiles():model.cc:323) Loading RNNLM model from /usr/share/vosk/vosk-model-de-0.21/rnnlm/final.raw
INFO:root:Wrong argumentsMy Subtitleswitcher Plugin looks like this (i also tried to place vosk model in other folders before):
subtitleDivStyle:
3px
[ ] disableSubtitleSettings
[ ] disableUTF8Encode
[X] addClosedCaptionIcons
[ ] defaultSubtitleIsOff
defaultSubtitleLanguage:
de
[ ] defaultSubtitleLanguageUseUserLocation
[X] automaticTranscript
automaticTranscriptModelPath:
/usr/share/vosk/vosk-model-de-0.21did i miss or misunterstand something?
DanielnetoDotCom
walt93
Hey Folks,
I have just enabled the Subtitleswitcher Plugin and tried to enable the automatic voice transcription for my videos.
I am not sure about how this should work. I have read this (https://github.com/WWBN/AVideo/wiki/Video-Transcription-for-the-SubtitleSwitcher-Plugin#the-transcriber) and this (https://alphacephei.com/vosk/install)
python3 --version
Python 3.11.2pip3 --version
pip 23.0.1 from /usr/lib/python3/dist-packages/pip (python 3.11)I tried with all model packs that are available for my language "german".
Here is my problem as far as i was able to find out: There is a .srt.log file and (not always but often) a .srt file inside of each video folder. The .srt file, if it exists is empty. Sometimes there is a .vtt file in this folder (i understood that there should be the closed caption content inside, shouldnt it?). The .vtt file contains only
WEBVTT. Those files are generated by the plugin, correct?The content of the .srt.log file is
In my AVideo.log i find this line (where '155' is the ID of the video that the plugin is trying to transcribe, right?).
Vosk seems to work properly. When i try to test it with one of the mp4 files e.g., it recognizes every word.
vosk-transcriber -i test.mp4 -o test.txtDoes anyone have a hint?