# Efficient inference acceleration

This is the CTranslate2 converted version of the OpenAI Whisper large-v1 model for efficient speech recognition tasks

This project converts the openai/whisper-medium model to the CTranslate2 model format, which can be used for efficient speech recognition.

The Whisper base model is an Automatic Speech Recognition (ASR) model developed by OpenAI, supporting speech-to-text tasks in multiple languages.

I-BERT is a pure integer-quantized version of RoBERTa-large, using INT8 to store parameters and integer operations for inference, achieving up to 4x inference acceleration.

SEW-D is a compressed and efficient speech pre-training model developed by ASAPP Research, pre-trained on 16kHz sampled speech audio, suitable for various downstream speech tasks.