From e1d77e4205263bf6cd20cb64734b73ebadc487cd Mon Sep 17 00:00:00 2001
From: makaveli10 <suryanvineet47@gmail.com>
Date: Tue, 8 Aug 2023 14:18:15 +0800
Subject: [PATCH] update readme dockerfile cpu/gpu

---
 README.md | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/README.md b/README.md
index 966e813..bb9c48c 100644
--- a/README.md
+++ b/README.md
@@ -58,16 +58,19 @@ This would start the websocket server on port ```9090```.
 - Refer to [Audio-Transcription-Firefox](https://github.com/collabora/whisper-live/tree/main/Audio-Transcription-Firefox#readme) to use Mozilla Firefox extension.
 
 ## Whisper Live Server in Docker
-- Build docker container
-```bash
- docker build . -t whisper-live
-```
-
-- Run docker container
+- GPU
 ```bash
+ docker build . -t whisper-live -f docker/Dockerfile.gpu
  docker run -it --gpus all -p 9090:9090 whisper-live:latest
 ```
 
+- CPU
+```bash
+ docker build . -t whisper-live -f docker/Dockerfile.cpu
+ docker run -it -p 9090:9090 whisper-live:latest
+```
+**Note**: By default we use "small" model size. To build docker image for a different model size, change the size in server.py and then build the docker image.
+
 ## Future Work
 - [ ] Add translation to other languages on top of transcription.
 - [ ] TensorRT backend for Whisper.