Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitask model that can perform multilingual speech recognition as well as speech translation and language identification.
Features
Current release (v1.8.1) supports following whisper models:
Quick Usage
=== ":octicons-file-code-16: CPU"
```shell
docker run -d -p 9000:9000 -e ASR_MODEL=base -e ASR_ENGINE=openai_whisper onerahmet/openai-whisper-asr-webservice:latest
```=== ":octicons-file-code-16: GPU"
```shell
docker run -d --gpus all -p 9000:9000 -e ASR_MODEL=base -e ASR_ENGINE=openai_whisper onerahmet/openai-whisper-asr-webservice:latest-gpu
```for more information: