ggml-org/whisper.cpp

An option to stream audio files?

Open

#744 opened on Apr 11, 2023

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

Description

I want to benchmark streaming on a bunch of audio samples. It would be swift and efficient if the "stream" cli could input audio files and internally stream them.

Can we have this feature added to streaming? It would definitely make large-scale benchmarking of streaming whisper cpp very easy.

Contributor guide

Tech stack
cpp
Domain
cliperformance
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.
mostly clear
Prerequisites
C++ knowledgewhisper.cpp streamingaudio file handling
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
35
Research direction
The issue asks for adding an option to stream audio files in the 'stream' CLI. Investigate the current stream implementation (likely in examples/ or main.cpp) and how audio input is handled. Look for existing audio file reading utilities. Review any comments on the issue for maintainer feedback. Consider modifying the stream command to accept file paths and internally stream them to the model.
An option to stream audio files? · ggml-org/whisper.cpp#744 | Good First Issue