Switch text-to-image and automatic speech recognition (ASR) back to using the Hugging Face inference client; Zero GPU cannot accommodate the time it takes for those tasks

Enable low CPU memory usage with `accelerate` during model loading, which is useful on Hugging Face Spaces and other memory-constrained environments

Switch to use GPU instead of inference client

Add translation to English sample with automatic source language detection

Updated code to address “UserWarning: You have not specified a value for the `type` parameter”

Move environment variable querying code out of the Gradio UI-construction functions all the way to the root of the application, `app.py`

Move environment variable querying code out of the inference functions

Add required `espeak`

Add documentation

Reorganize structure for even less code clutter; `app.py` is greatly slimmed down

Swap button and output for image captioning sample

AI-generated chat sample revision 1: support both seq2seq and causal LM models

Add AI-generated chat sample

Enable audio file retrieval by URL for automatic speech recognition (ASR) sample

Switch the automatic speech recognition (ASR) implementation to use the inference client instead

Add automatic speech recognition (ASR) sample

Add text-to-speech (TTS) sample

Remove explicit PyTorch packages from `requirements.txt`

Add image captioning sample

Reorganize structure for less code clutter

Initial gallery

Add Hello World application file

initial commit