Ecosyste.ms: Awesome

https://github.com/sugarcane-mk/whisper

This repository provides a Python script for extracting speech embeddings using OpenAI's Whisper model. The embeddings are high-dimensional feature vectors that capture the acoustic properties of the input audio. These embeddings can be used for downstream tasks such as speech classification, clustering, and speaker recognition.

asr classification feature-extraction openai speech-processing speech-recognition speech-to-text svm-classifier whisper

Last synced: 09 Nov 2024