Merge pull request #14 from makaveli10/dockerize

Add Dockerfile.

Dockerfile

@@ -0,0 +1,44 @@
+FROM nvidia/cuda:11.2.2-cudnn8-devel-ubuntu20.04
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+# Remove any third-party apt sources to avoid issues with expiring keys.
+RUN rm -f /etc/apt/sources.list.d/*.list
+
+# Install some basic utilities.
+RUN apt-get update && apt-get install -y \
+    curl \
+    ca-certificates \
+    sudo \
+    git \
+    bzip2 \
+    libx11-6 \
+ && rm -rf /var/lib/apt/lists/*
+
+RUN apt update
+
+# install python
+RUN apt install software-properties-common -y && \
+    add-apt-repository ppa:deadsnakes/ppa && \
+    apt update
+
+RUN apt install python3-dev -y && \
+    apt install python-is-python3
+    
+
+# install pip
+RUN apt install python3-pip -y
+
+# Create a working directory.
+RUN mkdir /app
+WORKDIR /app
+
+COPY setup.sh /app
+COPY requirements/ /app
+
+RUN bash setup.sh
+RUN pip install -r server.txt
+
+COPY *py /app
+
+CMD ["python", "server.py"]

README.md

@@ -46,13 +46,28 @@ Unlike traditional speech recognition systems that rely on continuous audio stre
 ```
 This would start the websocket server on port ```9090```.
 
+### Chrome Extension
+- Head over to ```Audio-Transcription``` module to unpack and load a chrome extension to capture any audio in the browser and send it to the websocket server to transcribe the audio in the current tab.
 
-- Head over to ```Audio-Transcription``` module to unpack and load a chrome extension to capture any audio in the browser(only Chrome for now) and send it to the websocket server to transcribe the audio in the current tab.
+### Firefox Extension
+- 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
+```bash
+ docker run -it --gpus all -p 9090:9090 whisper-live:latest
+```
 
 
 ## Future Work
 - [ ] Update Documentation.
-- [ ] Keep only a single server implementation i.e. websockets and get rid of the socket implementation in ```server.py```. Also, update ```client.py``` to websockets-client implemenation.
+- [x] Keep only a single server implementation i.e. websockets and get rid of the socket implementation in ```server.py```. Also, update ```client.py``` to websockets-client implemenation.
 - [ ] Add translation to other languages on top of transcription.
 
 ## Citations

requirements/server.txt

@@ -1,6 +1,6 @@
 PyAudio
 faster-whisper==0.6.0
-paho-mqtt
---extra-index-url https://download.pytorch.org/whl/cu113
-torch==1.12.1
+--extra-index-url https://download.pytorch.org/whl/cu111
+torch==1.10.1
+torchaudio==0.10.1
 websockets

server.py

@@ -277,5 +277,5 @@ class ServeClient:
     
 
 if __name__ == "__main__":
-    with serve(recv_audio, "127.0.0.1", 9090) as server:
+    with serve(recv_audio, "0.0.0.0", 9090) as server:
         server.serve_forever()