A live, real-time transcription of the audio based on OpenAI's Whisper API.
Project description
Live Transcribe
Live Transcribe is a Python package that provides live, real-time transcription of audio based on OpenAI's Whisper API.
Currently, Live Transcribe supports only PulseAudio as an audio backend.
Installation
- optional but highly recommended for low latency Refer to the Pytorch documentation guide to install Pytorch with CUDA support.
pip install live-transcribe
Usage
Just run:
python -m live_transcribe
On the first usage, the OpenAI's Whisper model will be downloaded and cached.
See live_transcribe --help
for options.
Dependencies
Live Transcribe has the following dependencies:
Python 3.8 or higher
OpenAI-Whisper
PulseAudio
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
live-transcribe-0.1.0.tar.gz
(8.3 kB
view hashes)
Built Distribution
Close
Hashes for live_transcribe-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8391b0ef3ce38f2abec3192272ff66ad81daa53551df0de1dc1659518238dfad |
|
MD5 | efcd9597d37f1b1c7a3a04fe5dbf0cbe |
|
BLAKE2b-256 | a21197e59e3a308afeb8d2063f4badf0869cb709ad3c1fd51673eeff366873bd |