Merge pull request #26 from beeldengeluid/22-gpu-docker

22 gpu docker

Dockerfile

@@ -1,11 +1,15 @@
-FROM docker.io/python:3.10
+FROM nvidia/cuda:12.2.2-cudnn8-runtime-ubuntu22.04
 
 # Create dirs for:
 # - Injecting config.yml: /root/.DANE
 # - Mount point for input & output files: /mnt/dane-fs
 # - Storing the source code: /src
 RUN mkdir /root/.DANE /mnt/dane-fs /src /data
 
+RUN apt-get update && \
+    apt-get install -y python3-pip python3-dev python-is-python3 && \
+    rm -rf /var/lib/apt/lists/*
+
 WORKDIR /src
 
 ENV POETRY_NO_INTERACTION=1 \

README.md

@@ -12,4 +12,12 @@ The Whisper model version can be adjusted in the `config.yml` file by editing th
 |`medium`|769 M|
 |`large`|1550 M|
 |`large-v2`|1550 M|
-|`large-v3`|1550 M|
+|`large-v3`|1550 M|
+
+We recommend version `large-v2` as it performs better in most cases than `large-v3`.
+
+## Running via Docker using a CUDA compatible GPU
+
+To run it using a GPU via Docker, check [the instructions from the dane-example-worker](https://github.com/beeldengeluid/dane-example-worker/wiki/Containerization#running-the-container-locally-using-cuda-compatible-gpu).
+
+Make sure to replace `dane-example-worker` in the `docker run` command with `dane-whisper-asr-worker`.

config/config.yml

@@ -30,7 +30,7 @@ OUTPUT:
     S3_FOLDER_IN_BUCKET: folder  # folder within the bucket
 WHISPER_ASR_SETTINGS:
     WORD_TIMESTAMPS: True
-    DEVICE: cpu  # "cpu" to run on CPU, otherwise "cuda" to run on GPU
+    DEVICE: cuda  # "cpu" to run on CPU, otherwise "cuda" to run on GPU
     VAD: True  # whether to use voice activity detection (VAD) or not
     MODEL_VERSION: large-v2  # check the README for available options
     BEAM_SIZE: 5