WebUI process dies immediately when finishing transcription

[conlanpatrek]

Running on Windows 11,
CUDA (NVidia RTX 3090)
python 3.10.6

Server is run with subsai-webui --server.maxUploadSize 50000 in case that's relevant.

using faster-whisper and large-v2

Trying to process a 1hr 17min wav file, just under 900mb. It gets to the final segment it just shuts down with no error message, as if the process exited successfuly. The UI does not get updated, and the transcriptions are inaccessible. Tried both headless and no. No difference. Can't actually export srts from the UI because of this. I was hoping to use the webui because i have other AI generative stuff on this server, but work on different computers at home.

I do get an occasional message on the ui that says "Connection failed with status 0"

Not sure what i'm doing wrong here. LMK what other details you need.

[abdeladim-s]

@conlanpatrek,
Could you please provide more details ? There are no errors on the terminal ?

• Is the issue occur with just this file ?
• Have you tried the CLI ?
• If you running it on a remote server, have you tried then to try with Docker first ?

[conlanpatrek]

• No errors in the terminal, it the process just ends after finishing transcribing
• it does work with these settings on shorter files. I can recreate it with longer ones though.
• cli works fine, so that's what i've been using instead,
• i do access this from a remote client on the local net, but the behavior is the same when i access from the machine