ggml-org/whisper.cpp

whisper.wasm : update Emscripten bridge to provide text segments and token data to the JS layer

Open

#585 opened on Mar 8, 2023

View on GitHub
 (4 comments) (0 reactions) (0 assignees)C++ (49,693 stars) (5,535 forks)batch import
enhancementgood first issue

Description

While Im testing the code I have seen that full_default do not return the data, just only logs it. To be able to retrieve them I have override the print and printErr handlers to extract the data and then apply clunky regexes. Could not be awesome if we could gather the output instead of the error code? Or both?

Contributor guide

Tech stack
cppjavascript
Domain
api
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
C++ knowledgeJavaScript knowledgeEmscripten basicswhisper.cpp codebase
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
45
Research direction
Examine current whisper.cpp Emscripten bridge implementation to understand how full default returns data. Modify C++ code to populate a result structure and expose it via JavaScript binding. Look at the example in the repository for guidance on how to implement the callback. Ensure the output includes text segments and token data.