Spaces:
Runtime error
Runtime error
| from transformers import ViTFeatureExtractor, ViTForImageClassification | |
| import gradio as gr | |
| from datasets import load_dataset | |
| import torch | |
| dataset = load_dataset("cifar100") | |
| image = dataset["train"]["fine_label"] | |
| def classify(image): | |
| feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224') | |
| model = ViTForImageClassification.from_pretrained('google/vit-base-patch16-224') | |
| inputs = feature_extractor(images=image, return_tensors="pt") | |
| with torch.no_grad(): | |
| outputs = model(**inputs) | |
| logits = outputs.logits | |
| # model predicts one of the 1000 ImageNet classes | |
| predicted_class_idx = logits.argmax(-1).item() | |
| return model.config.id2label[predicted_class_idx] | |
| def image2speech(image): | |
| txt = classify(image) | |
| return fastspeech(txt), txt | |
| fastspeech = gr.Interface.load("huggingface/facebook/fastspeech2-en-ljspeech") | |
| app = gr.Interface(fn=image2speech, | |
| inputs="image", | |
| title="Image to speech", | |
| description="Classifies and image and tell you what is it", | |
| examples=["remotecontrol.jpg", "calculator.jpg", "cellphone.jpg"], | |
| allow_flagging="never", | |
| outputs=["audio", "text"]) | |
| app.launch() |