Collected molecules will appear here. Add from search or explore.
Provides a real-time streaming wrapper for OpenAI's Whisper model to perform low-latency speech-to-text on live audio input.
stars
36
forks
10
This project is a thin wrapper around Hugging Face Transformers and Whisper. With only 36 stars and no recent activity, it lacks the optimizations found in more mature streaming implementations like faster-whisper or whisper.cpp. Frontier labs and specialized ASR providers (Deepgram, AssemblyAI) have already surpassed this capability with native streaming models.
TECH STACK
INTEGRATION
cli_tool
READINESS