testing

app.py

@@ -1,20 +1,16 @@
 import streamlit as st
-from transformers import pipeline
-from PIL import Image
+from transformers import AutoProcessor, SeamlessM4Tv2ForTextToText
 
-pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
+processor = AutoProcessor.from_pretrained("facebook/seamless-m4t-v2-large")
 
-st.title("Hot Dog? Or Not?")
+model = SeamlessM4Tv2ForTextToText.from_pretrained("facebook/seamless-m4t-v2-large")
 
-file_name = st.file_uploader("Upload a hot dog candidate image")
 
-if file_name is not None:
-    col1, col2 = st.columns(2)
+text_inputs = processor(text = "Hello, my dog is cute", src_lang="eng", return_tensors="pt")
 
-    image = Image.open(file_name)
-    col1.image(image, use_column_width=True)
-    predictions = pipeline(image)
+# from text
+output_tokens = model.generate(**text_inputs, tgt_lang="fra", generate_speech=False)
+translated_text_from_text = processor.decode(output_tokens[0].tolist()[0], skip_special_tokens=True)
 
-    col2.header("Probabilities")
-    for p in predictions:
-        col2.subheader(f"{ p['label'] }: { round(p['score'] * 100, 1)}%")
+
+st.write(translated_text_from_text)