Whisper models for CTranslate2 with quantization INT8
This repository contains the conversion of OpenAI Whisper models to the CTranslate2 model format.
Conversion details
The original model was converted with the following command:
ct2-transformers-converter --model openai/<model name> --output_dir faster-<model name>-int8 \
--copy_files tokenizer.json --quantization int8
Note that the model weights are saved in INT8.
Models sources
Inference API (serverless) does not yet support ctranslate2 models for this pipeline type.