PythonAI
PythonAI copied to clipboard
unknown crash
For some reason... all I get is this:
(venv) craig@sam:~/Projects/PythonAI $ python alf.py catalan LOG (VoskAPI:ReadDataFiles():model.cc:213) Decoding params beam=13 max-active=7000 lattice-beam=6 LOG (VoskAPI:ReadDataFiles():model.cc:216) Silence phones 1:2:3:4:5:11:12:13:14:15 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 ./model/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 ./model/graph/HCLG.fst LOG (VoskAPI:ReadDataFiles():model.cc:294) Loading words from ./model/graph/words.txt LOG (VoskAPI:ReadDataFiles():model.cc:303) Loading winfo ./model/graph/phones/word_boundary.int LOG (VoskAPI:ReadDataFiles():model.cc:310) Loading subtract G.fst model from ./model/rescore/G.fst LOG (VoskAPI:ReadDataFiles():model.cc:312) Loading CARPA model from ./model/rescore/G.carpa Killed (venv) craig@sam:~/Projects/PythonAI $
That is running on my Raspberyy PI4B directly... with a 3.9.2 venv.
I've also tried this on my local fedora36 laptop... running under both python 3.7,3.9 & 3.10 venv's... when it crashes while running it in the IDE (both vcode and pycharm) it actually just kills the IDE dead for some reason.
I have no idea how to debug this... as it seems to be at the end of the vosk init.. my only thought could be that its somehow related to that?
Did you download the model files from https://alphacephei.com/vosk/models and unzip to the project root folder, and rename the folder to model?
[Edit]
Actually, it looks like you have, what about trying the small model (40MB) - how much memory has your laptop got? The big version says it requires up to 16GB of RAM.
good call... yes, that fixed it...
I started from a whole new venv... did a git clone... downloaded the 40m model... and the only changes I had to make it work was remove the pyobjc requirements and remove the skills.mirror
those small changes and it works fine now.. thanks!
what did the skills.mirror do wrong...