chore: update docker tag to latest

README.md

@@ -20,9 +20,9 @@ See [OpenAI API reference](https://platform.openai.com/docs/api-reference/audio)
 ## Quick Start
 Using Docker
 ```bash
-docker run --gpus=all --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface fedirz/faster-whisper-server:0.1-cuda
+docker run --gpus=all --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface fedirz/faster-whisper-server:latest-cuda
 # or
-docker run --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface fedirz/faster-whisper-server:0.1-cpu
+docker run --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface fedirz/faster-whisper-server:latest-cpu
 ```
 Using Docker Compose
 ```bash

compose.yaml

@@ -1,7 +1,7 @@
 # NOTE: arm images haven't been tested
 services:
   faster-whisper-server-cuda:
-    image: fedirz/faster-whisper-server:0.1-cuda
+    image: fedirz/faster-whisper-server:latest-cuda
     build:
       dockerfile: Dockerfile.cuda
       context: .
@@ -23,7 +23,7 @@ services:
           devices:
             - capabilities: ["gpu"]
   faster-whisper-server-cpu:
-    image: fedirz/faster-whisper-server:0.1-cpu
+    image: fedirz/faster-whisper-server:latest-cpu
     build:
       dockerfile: Dockerfile.cpu
       context: .

examples/live-audio/script.sh

@@ -10,9 +10,9 @@ set -e
 export WHISPER_MODEL=Systran/faster-distil-whisper-large-v3 # or Systran/faster-whisper-tiny.en if you are running on a CPU for a faster inference.
 
 # Ensure you have `faster-whisper-server` running. If this is your first time running it expect to wait up-to a minute for the model to be downloaded and loaded into memory. You can run `curl localhost:8000/health` to check if the server is ready or watch the logs with `docker logs -f <container_id>`.
-docker run --detach --gpus=all --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface --env WHISPER_MODEL=$WHISPER_MODEL fedirz/faster-whisper-server:0.1-cuda
+docker run --detach --gpus=all --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface --env WHISPER_MODEL=$WHISPER_MODEL fedirz/faster-whisper-server:latest-cuda
 # or you can run it on a CPU
-# docker run --detach --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface --env WHISPER_MODEL=$WHISPER_MODEL fedirz/faster-whisper-server:0.1-cpu
+# docker run --detach --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface --env WHISPER_MODEL=$WHISPER_MODEL fedirz/faster-whisper-server:latest-cpu
 
 # `pv` is used to limit the rate at which the audio is streamed to the server. Audio is being streamed at a rate of 32kb/s(16000 sample rate * 16-bit sample / 8 bits per byte = 32000 bytes per second). This emulutes live audio input from a microphone: `ffmpeg -loglevel quiet -f alsa -i default -ac 1 -ar 16000 -f s16le`
 # shellcheck disable=SC2002

examples/youtube/script.sh

@@ -6,9 +6,9 @@ set -e
 export WHISPER_MODEL=Systran/faster-distil-whisper-large-v3 # or Systran/faster-whisper-tiny.en if you are running on a CPU for a faster inference.
 
 # Ensure you have `faster-whisper-server` running. If this is your first time running it expect to wait up-to a minute for the model to be downloaded and loaded into memory. You can run `curl localhost:8000/health` to check if the server is ready or watch the logs with `docker logs -f <container_id>`.
-docker run --detach --gpus=all --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface --env WHISPER_MODEL=$WHISPER_MODEL fedirz/faster-whisper-server:0.1-cuda
+docker run --detach --gpus=all --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface --env WHISPER_MODEL=$WHISPER_MODEL fedirz/faster-whisper-server:latest-cuda
 # or you can run it on a CPU
-# docker run --detach --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface --env WHISPER_MODEL=$WHISPER_MODEL fedirz/faster-whisper-server:0.1-cpu
+# docker run --detach --publish 8000:8000 --volume ~/.cache/huggingface:/root/.cache/huggingface --env WHISPER_MODEL=$WHISPER_MODEL fedirz/faster-whisper-server:latest-cpu
 
 # Download the audio from a YouTube video. In this example I'm downloading "The Evolution of the Operating System" by Asionometry YouTube channel. I highly checking this channel out, the guy produces very high content. If you don't have `youtube-dl`, you'll have to install it. https://github.com/ytdl-org/youtube-dl
 youtube-dl --extract-audio --audio-format mp3 -o the-evolution-of-the-operating-system.mp3 'https://www.youtube.com/watch?v=1lG7lFLXBIs'