manuelsh / whisper-container

Container to be used with S3 and AWS Batch.

Whisper container

The following creates a container that takes an audio file from S3, runs whisper model to transcribe it, and returns the transcription to S3.

It's intended to be used in AWS Batch service.

Pushing it to docker hub

For this image to run it needs to be pushed to docker hub. For that you need to login first using:

docker login

Then you can push the image using:

docker push manuelsh/platic-whisper:latest

File types accepted

The container takes .flac files from S3 with 16000 Hz sample rate.

Variables

The docker uses the following environment or config variables:

In the config.py file:

• WHISPER_MODEL: whisper model type, set to large.
• S3_CREDENTIALS_PATH: http path to S3 credentials from ec2 AIM role.
• S3_BUCKET: S3 bucket where input and output files are stored.

Also, one must run the container with the following environment variables:

• FILE_NAME: name of the file to transcribe. The output file will have the same name with a _result.json suffix.
• LANGUAGE: the language of the audio file. To autodetect the language, set to auto.
• TASK: the task to run. Set to transcribe to transcribe the audio file or translate to translate the transcription to English.

Running the container

The following command builds the container locally, as an example:

docker build -t whisper .

and as an example to run it:

docker run \
 -e FILE_NAME=b3l01m3ahMQ9pR7DP9DSU5Ukba33_1960547e-d418-40c1-961b-805037a1645e.flac \
 -e LANGUAGE=es \
 -e TASK=transcribe \
 --entrypoint python3 -u main.py\
 -it whisper