-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
STT0073: LLM-Based Correction of Inference Transcriptions Using Claude AI #3
Comments
@kaldan007 and @gangagyatso4364, could you please review my card? |
add the step to make cer comparison between all three kinds of transcript generated at last. |
looks good go ahead. |
@gangagyatso4364, could you please review my updated card? |
|
Transfer_text Based CorrectionNo Spelling Mistake in Inference Transcript:
Correction of Spelling Mistake:
|
རྒྱ་ནག་གཞུང་གིས་མཚོ་སྔོན་ཞིང་ཆེན་མགོ་ལོག་ཁུལ་བཙུགས་ནས་ལོ་འཁོར་ ༧༠ འཁོར་བའི་མཛད་སྒོ་འཚོགས་ཡོད་པ་བཞིན། |
Description:
Develop a pipeline to process audio transcription data by parsing the catalog, segmenting audio, and generating inference transcriptions. Validate and correct the transcriptions using an LLM to align them with reference texts while preserving context. Save corrected transcriptions and metadata to a structured CSV, with logs capturing errors and issues.
Resources:
Completion Criteria:
Implementation:
Updated Subtasks:
This updated approach reflects the intermediate creation of a Transfer Text CSV file using the
transfer_text
function and its role in correcting the split audio inference transcriptions.Card Reviewer: @kaldan007
The text was updated successfully, but these errors were encountered: