DebasishDhal99/all-in-one-translation

Update app.py

Update app.py

Update app.py

sad: decomissioning image to text feature due to a sudden google translator api limit

Update backend/image_to_tgt.py

fix: fixing rate limit issue by avoiding any google translator api call outside functions

fix: hardcoded the available languages because dynamic loading of available langauges was re-crashing the system (google translate rate limit)

Update pydantic version in requirements.txt t comply with gradio

Comment out audio processing and translation code

Disable audio translation interface

Comment out openai-whisper dependency

fix: Add setuptools requirement to pre-requirementx.txt

fix: Downgrade Python version and added it README

Update workflow to remove auto deployment to huggingface

fix: Update SDK version from 5.12.0 to 5.30.0 in README

fix: Update GitHub Actions workflow with correct usernamef

Gradio downgrade, pydantix fix, readme logs update

API import fix

Remove API dependency for lang detection using langdetect lib

Add logs of api usage limit overshoot

Interface descriptions polishing

Readme edit

Fix import from image file

Fix examples for target lang in image

Add target lang option for image

Audio src_lang error fix

Simplifying dependencies in audio part

Add target lang option to audio translation. Edit

Add target lang option to audio translation

Remove default value for txt, it created conflicts

Rectify single_detection in text_to_tgt

Add source language detection

Add target lang option to txt translation

Rectify example input methods for audio and images

Add example images/audio, add example parameter in app.py

Add full language name for whisper

Add transcribed original text, original language for whisper

Add model size options for whisper

change git push to got push --force

Create main.yml for git->hf sync

Add demos to readme

Add translate feature to audio

add pydub library for audio manipulation

add pydub to manipulate audio objects

replace openai library with whisper

add whisper model

Add input audio processing

change api variable name

add free api key

fix syntax issue