Tags

Release 2.1.0
- Endpoint audio_to_text added to get transcription from audio

Release 2.0.0
- Support for arabic and russian languages was added to functionality. Also support to more audio and image formats was added, using converters.

Release 1.0.0
- Dockerizing app, update necessary modules and read.md for docker container

Updated audio_split_by_strings with additional return of original strings and transcription of audio by choosing parameter

Release 0.3.0
- Endpoint image_to_strings added to return sentences, recognized from image

Release 0.2.0
- Endpoint audio_split_by_image to split audio, based on text from image (added instaed of image_to_text and audio_to_text to join them)

Release 0.1.0
- Endpoint image_to_text to get last words of sentences, recognized from image
- Endpoint audio_to_text to get sentences, recognized from audio