As a machine learning engineer and open-source enthusiast, I've always been driven by the desire to create solutions that bridge the gap between technological capability and universal accessibility.
Out of this pursuit, Wordcab Transcribe was born - a FastAPI based API for transcribing audio files using Faster-Whisper and NVIDIA NeMo.
This journey of creating an open-source, production-ready transcription service has been both challenging and rewarding.
Automatic Speech Recognition (ASR) has become an essential tool for developers and businesses. With Wordcab Transcribe, you can leverage ASR in your projects without relying on expensive third-party platforms.
We've implemented an open-source ASR solution using Docker, FastAPI, and the faster-whisper library, which is a fast implementation of the transcription model from OpenAI Whisper.
This project utilizes CTranslate2 under the hood to speed up the processing of audio files while requiring less than 5GB of VRAM on the GPU with the large-v2 Whisper model.
In this blog post, we'll present the Wordcab Transcribe project and show you how to use it in your own applications.