I am try to analyze audio file by converting audio to text, but along with that I also want speaker tagged to the text.
If in audio file there are two people conversation then I should get text with speaker 1 / speaker 2.
Please suggest any open source libraries or other ways to do in python.
Thanks in advance for help.
I fixed it for you, but given that a non-trivial number of other users have made the same mistake, could you explain what about the “Python Software Foundation” category name or or short description,
This category is for the discussions relating to the [Python Software Foundation](Python Software Foundation | Python Software Foundation
led you to post a general help question in this category, near the very bottom of the list, instead of the “Users” category at the very top? Is there something that is confusing, or is there something we can improve to avoid others making this same mistake in the future? We’d appreciate any insight you can provide on this, thanks.
As to your question, what you want is a speech recognition library for Python, of which there are a number. A web search reveals a variety of options, as well as potentially useful guides for beginners.
Best of luck!
I know there are many speech recognition libraries, but i need library which will separate speakers and get there audio / text from the audio file or Speaker Diarization.
I modified the search accordingly, which looks like its returning some decent results.
In general, while we can try to help, keep in mind that this Discourse is primarily for discussion of and help with the core Python language, and other resources are likely to provide more appropriate help with third party packages and specialized needs like this.
Also, as a disclaimer, my reply was mostly as a courtesy in the context of asking you as to the reasons for the confusion over the category (which I’d appreciate an answer to, BTW…) and I don’t have particular expertise in this area.
Best of luck!