Is There an Audio Processing Application from OpenVINO™ Toolkit?

Unable to find an audio processing application from OpenVINO™ Toolkit.

OpenVINO provides several Jupyter* notebooks for speech recognition that demonstrate how to optimize and deploy models such as Whisper*, Distil-Whisper*, and MMS.

Key Notebooks and Models:

• Speech to Text with OpenVINO: This tutorial provides a general, step-by-step guide for performing speech-to-text recognition, including model downloading, conversion to OpenVINO IR format, audio processing, and output decoding.
• Automatic speech recognition using Distil-Whisper and OpenVINO: This notebook focuses on using the faster and smaller Distil-Whisper model, which performs nearly as well as the original Whisper with fewer parameters. It also demonstrates how to use the Hugging Face* Optimum library for easy conversion and integration.
• Automatic speech recognition using Whisper and OpenVINO with Generate API: This notebook details the use of the original OpenAI Whisper model, showcasing the OpenVINO Generate API for enhanced user experience and performance.
• MMS: Scaling Speech Technology to 1000+ languages with OpenVINO: This example covers the Massively Multilingual Speech (MMS) project models, which support over 1,100 languages, including an interactive demo using Gradio.