watson-developer-cloud / speech-to-text-websockets-python

Python client that interacts with the IBM Watson Speech To Text service through its WebSockets interface
http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercloud/speech-to-text.html
86 stars 63 forks source link

is there a limit around 20 minutes? #7

Closed berio closed 8 years ago

berio commented 8 years ago

Hi, first of all, thank you for your script. It really helped me a lot. I noticed that when I try to transcribe a large file, like for example one of 60 minutes, it stops transcribing around minute 22-23. I tried using several audio files, and it always finishes around that time. Is there any time constraints or some configuration that I am missing? Are you aware of this limitation?

Thank you very much

nfriedly commented 8 years ago

There's a limit of 100mb, that could be the issue. Is it feasible to break your audio into smaller chunks? (And/or compress it with FLAC or Opus?)

berio commented 8 years ago

Ok, my audio is around 150 MB. That could be the issue then. I'll try to compress it. Thank you very much!

daniel-bolanos commented 8 years ago

Hi, I'm glad you are finding the script helpful. Yes, if the file is large then it is better to compress it so you do not run into the 100MB limitation. With opus or flac you can get 10x or 5x compression.

Dani