| from onnxt5 import GenerativeT5 | |
| from onnxt5.api import get_encoder_decoder_tokenizer | |
| import gradio as gr | |
| decoder_sess, encoder_sess, tokenizer = get_encoder_decoder_tokenizer() | |
| generative_t5 = GenerativeT5(encoder_sess, decoder_sess, tokenizer, onnx=True) | |
| def inference(prompt): | |
| output_text, output_logits = generative_t5(prompt, max_length=100, temperature=0.) | |
| return output_text | |
| gr.Interface(inference,"text","text").launch() |