Audio transcriber #25
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add textarea for transcript input, add summarise button which extracts transcript. Currently only alerts, summary not yet implemented.
…ranscript timestamped by slides
Connect GPT 3.5 API in orde to mae summary requests. Not yet linked to frontend.
openai-test.js can now be run with nodes openai-test.js "your-transcript-here" to output the summary of the argument given.
Extract the message content from the completion returned by the GPT API rather than the entire response
Added an abstract class that is extended by the classes that contain transcripts of the whole lecture and transcripts split by slides
define plan for document format based on classes in IR branch. (These classes such as Transcript, Slide etc. are not present yet on this branch.) classes Slide, Transcript etc. are not yet on this branch
Move openai-test.js code into Summariser class to use with summariser tests
Change Summariser argument type from string to String
Resolve summary in summariser_tests.js and set to new variable if it isn't null (initialised to empty string).
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
|
This was
linked to
issues
Jan 19, 2024
Replace switch statement with if else to fix summariser customisations
FFmpeg does not exit when video with no audio is the input file
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
In
src/lib/transcriber.ts:transcribe()is the exported function to integrate into the next stage of the projectextract_audio()usedfluent-ffmpegto take in a.mp4video from the filesystem and output a.mp3audio file back to the filesystem.run_query()imports an audio file, and queries theWhisper-large-v3Inference API to transcribe the video.We need to find out the limit of file size/audio length that the fast prototyping can take in, so we can run the API in chunks (this slows down the code significantly). The other options are: paying for the development API to run longer videos; or taking the API as a python module (ask @VrishYT for more details on that).