Skip to content

Add RubyLLM.transcribe method. #97

New issue

Have a question about this project? # for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “#”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? # to your account

Open
wants to merge 4 commits into
base: main
Choose a base branch
from

Conversation

keithrbennett
Copy link
Contributor

Add top level transcribe method to match chat, embed, paint. Addresses #92 .

@keithrbennett keithrbennett marked this pull request as draft April 4, 2025 16:41
Add Transcription module to Providers::OpenAI.
Model now defaults to whisper-1 and does not need prompt.
Add transcription docs.
Make transcription model default a config option.
Enhance Content.mime_type_for to support audio content types.
Simplify RubyLLM unit tests to only test that correct methods are called, no LLM access.
# Conflicts:
#	lib/ruby_llm/configuration.rb
@keithrbennett keithrbennett marked this pull request as ready for review April 9, 2025 16:01
@keithrbennett
Copy link
Contributor Author

@crmne I believe this PR is ready. It took a surprising amount of code and time to implement, but I think it adds value beyond a simple transcribe method and is a good addition to the code base. I hope you think so too! :)

@schappim
Copy link

@crmne any chance of getting this merged? 🙏

# for free to join this conversation on GitHub. Already have an account? # to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants