Felix Spöttel 52ce148605 fix: bind http
2023-03-15 13:46:24 +01:00
2023-02-08 14:45:18 +01:00
2022-12-27 11:35:08 +01:00
2023-03-15 12:37:44 +01:00
2023-03-15 12:37:44 +01:00
2023-02-08 15:51:31 +01:00
2023-01-28 12:30:02 +01:00
2023-03-15 12:37:44 +01:00
2023-03-15 12:37:44 +01:00
2023-03-15 13:46:24 +01:00
2023-03-15 13:46:24 +01:00
2023-03-15 12:37:44 +01:00
2023-03-15 13:46:24 +01:00
2023-03-01 17:55:06 +01:00

whisperbox-transcribe

HTTP wrapper around openai/whisper.

API documentation

OpenAPI documentation can be accessed via <service_url>/docs.

Deploy

  1. Clone this repository to the host machine.
  2. Create an .env file from .env.example.
  3. Run make run to start the server.
  4. Wrap in a systemd service to launch at startup.

Develop

docker compose is required for local development.

It is recommended to setup a virtual environment for python tooling. To install dependencies in your virtual env, run pip install -e .[tooling,web,worker].

Copy .env.test to .env to configure the service.

Start

make dev

Builds and starts the docker containers.

# Bindings
http://localhost:5555                   => Celery dashboard
http://whisperbox-transcribe.localhost  => API
http://whisperbox-transcribe.localhost  => API docs
./whisperbox-transcribe.sqlite          => Database

Destroy

This removes all containers and attached volumes.

make clean

Test

make test

Lint

make lint

Format

make fmt
Description
Easy to deploy API for transcribing and translating audio / video using OpenAI's whisper model.
Readme 309 KiB
Languages
Python 90.1%
Dockerfile 6.7%
Makefile 1.8%
Mako 1.4%