diff --git a/README.md b/README.md index 720fb7e21aa241647a3325097ca76f22d24da1f2..74aa98f5625d511b1ab61f452d2fcf76177bff6c 100644 --- a/README.md +++ b/README.md @@ -6,6 +6,13 @@ Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification. For more details: [github.com/openai/whisper](https://github.com/openai/whisper/) +## Features +Current release (v1.1.0) supports following whisper models: + +- [openai/whisper](https://github.com/openai/whisper)@[v20230314](https://github.com/openai/whisper/releases/tag/v20230314) +- [faster-whisper](https://github.com/guillaumekln/faster-whisper)@[0.4.1](https://github.com/guillaumekln/faster-whisper/releases/tag/v0.4.1) +- [whisper.cpp](https://github.com/ggerganov/whisper.cpp) (Coming soon) + ## Usage Whisper ASR Webservice now available on Docker Hub. You can find the latest version of this repository on docker hub for CPU and GPU. @@ -71,10 +78,17 @@ poetry run gunicorn --bind 0.0.0.0:9000 --workers 1 --timeout 0 app.webservice:a ``` With docker compose: + +For CPU: ```sh docker-compose up --build ``` +For GPU: +```sh +docker-compose up --build -f docker-compose.gpu.yml +``` + ## Quick start After running the docker image interactive Swagger API documentation is available at [localhost:9000/docs](http://localhost:9000/docs)