Update Traffic_Signs_Classification.py

Traffic_Signs_Classification.py

@@ -3,17 +3,17 @@ from PIL import Image
 import torch
 from transformers import AutoImageProcessor
 import pandas as pd
-from transformers import pipeline
 from transformers import ViTForImageClassification
-
-
-
-model= ViTForImageClassification.from_pretrained('Rae1230/Traffic_Signs_Classification')
-processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224")
+from transformers import VitsModel, AutoTokenizer
+import torch
+from IPython.display import Audio
 
 # Streamlit application title
 st.title("Speech the Traffic Signs")
 
+#Traffic Sign Classification
+model= ViTForImageClassification.from_pretrained('Rae1230/Traffic_Signs_Classification')
+processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224")
 
 uploaded_file = st.file_uploader("Choose a PNG image...", type="png", accept_multiple_files=False)
 if uploaded_file is not None:
@@ -33,4 +33,18 @@ if uploaded_file is not None:
     text_col = df['Name']
     
     text_value = text_col.loc[num_col == img_class_idx].values[0]
-    st.write("Predicted class:", text_value)
+    st.write("Predicted class:", text_value)
+
+
+#speech the Traffic Sign
+
+model2 = VitsModel.from_pretrained("facebook/mms-tts-eng")
+tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-eng")
+
+text = text_value
+inputs = tokenizer(text, return_tensors="pt")
+
+with torch.no_grad():
+    output = model2(**inputs).waveform
+
+Audio(output.numpy(), rate=model2.config.sampling_rate)