wiseman
/ broadcastify_listen.py
Last active
April 18, 2025 12:02
Python 3 code for taking an mp3 stream, such as a police scanner feed from broadcastify, and running it through speech recognition.
This file contains hidden or 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
| """Does utterance segmentation and speech recognition on an mp3 stream | |
| (like from broadcastify...) | |
| Requires that ffmpeg be installed, and a Microsoft cognitive speech | |
| services API key | |
| (see https://azure.microsoft.com/en-us/try/cognitive-services/?api=speech-services). | |
| """ | |
| import audioop | |
| import collections |