olekenneth/WAAS

Whisper as a Service (Basic WIP API for transcribing speech)

WaaS - Whisper as a Service

Backend flask application for the Speech To Text service.

This service is powered by OpenAI Whisper

API Documentation

POST /v1/transcribe

Add a new transcribe job to the queue. The job will be processed by the worker asynchroniously.

The response will be a JSON object with job_id that can be used to check the status of the job.

Query parameters:

• REQUIRED: email_callback: string
• OPTIONAL: language: string (default: automatic detection)
• OPTIONAL: model: string (default: tiny)
• OPTIONAL: task: string (default: transcribe)
  • transcribe: Transcribe audio to text
  • translate: Transcribe then translate audio to text
• OPTIONAL: filename: string (default: untitled-transcription)

Body:

• REQUIRED: binary data: Raw data with the audio content to transcribe

OPTIONS /v1/transcribe

Get the available options for the transcribe route.

POST /v1/detect

Detect the language of the audio file.

Query parameters:

• OPTIONAL: model: string (default: tiny)

Body:

• REQUIRED: binary data: Raw data with the audio content to detect the language for

OPTIONS /v1/detect

Get the available options for the detect route.

GET /v1/download/<job_id>

Receive the finished job result as the requested output format.

Query parameters:

• OPTIONAL: output: string (default: srt)
  • json: JSON response of the model output
  • timecode_txt: Plain text file with timecodes(srt)
  • txt: Plain text file of the detected text
  • vtt: WebVTT file with the detected text
  • srt: WebVTT file with the detected text

OPTIONS /v1/download/<job_id>

Get the available options for the download route.

GET /v1/jobs/<job_id>

Get the status and metadata of the provided job.

GET /v1/queue

Get the available length of the queue as JSON object with the key length.

Contributing

Installation

python3 -mvenv .venv
source .venv/bin/activate
pip install -r requirements.txt

Running full setup using docker-compose

First create a .envrc file with the following content:

export BASE_URL=https://example.com
export EMAIL_SENDER_ADDRESS=example@example.com
export EMAIL_SENDER_PASSWORD=example
export EMAIL_SENDER_HOST=smtp.example.com

export DISCLAIMER='This is a <a href="example.com">disclaimer</a>'

Then run the following command

docker-compose --env-file .envrc up

This will start three docker containes.

• redis
• api running flask fra src
• worker running rq from src

Running full setup using devcontainers

Install remote-development extensions (containes) And then in vscode do Devcontaines: open folder in container Then you are inside the api-containe and can do stuff

curl

To upload a file called audunspodssounds.mp3 in norwegian from your download directory

curl --location --request POST 'localhost:5000/v1/transcribe?output=vtt' \
  --header 'Content-Type: audio/mpeg' \
  --data-binary '@/Users/<user>/Downloads/audunspodssounds.mp3'

Running tests

$ pytest

FAQ

How to fix [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate?

$ /Applications/Python\ 3.7/Install\ Certificates.command