diff --git a/README.md b/README.md index 74aa98f5625d511b1ab61f452d2fcf76177bff6c..a8ee3b03801464b2274f594657da1eab4352b1dd 100644 --- a/README.md +++ b/README.md @@ -1,8 +1,8 @@ -     +# Whisper ASR Webservice 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/) @@ -173,12 +173,3 @@ The ASR model is downloaded each time you start the container, using the large m ```sh docker run -d -p 9000:9000 -e ASR_MODEL=large -v //c/tmp/whisper:/root/.cache/whisper onerahmet/openai-whisper-asr-webservice:latest ``` - - -## TODO - -- Unit tests -- Recognize from path -- Batch recognition from given path/folder -- Live recognition support with HLS -- gRPC support diff --git a/docs/assets/img/banner.png b/docs/assets/img/banner.png deleted file mode 100644 index 8948e7c903e6b8c7f588622b498b4b39ddd92172..0000000000000000000000000000000000000000 Binary files a/docs/assets/img/banner.png and /dev/null differ