Everything you need to build a OpenAI Whisper (Speech to Text Transcription ML model) API, and associated docker container.
Link to the audio transcribed above.
- Clone this repo
- CD into the appropriate folder
docker build -t whisper .
- Takes about 3 minutes to build, depending on your machine
docker run -p 5000:5000 whisper
- Pitch MP3s at the endpoint, and recieve transcriptions as a JSON response object. Neat!