Create app.py

app.py

@@ -0,0 +1,35 @@
+import streamlit as st
+import tempfile
+import os
+from transformers import pipeline
+
+# Load the ASR model
+@st.cache_resource
+def load_model():
+    return pipeline("automatic-speech-recognition", model="ivrit-ai/whisper-large-v3-turbo")
+
+model = load_model()
+
+# Streamlit UI
+st.title("Hebrew Speech-to-Text Transcription")
+
+# Upload audio file
+uploaded_file = st.file_uploader("Upload an audio file (WAV, MP3, OGG)", type=["wav", "mp3", "ogg"])
+
+if uploaded_file is not None:
+    # Save the uploaded file to a temporary location
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as temp_audio:
+        temp_audio.write(uploaded_file.read())
+        temp_audio_path = temp_audio.name
+
+    # Transcribe the audio
+    st.write("Transcribing...")
+    try:
+        result = model(temp_audio_path)
+        st.subheader("Transcription:")
+        st.write(result["text"])
+    except Exception as e:
+        st.error(f"Error: {str(e)}")
+
+    # Clean up the temporary file
+    os.remove(temp_audio_path)