Create app.py

app.py

@@ -0,0 +1,25 @@
+import streamlit as st
+import soundfile as sf
+from transformers import pipeline
+import io
+
+# Load the model
+pipe = pipeline("automatic-speech-recognition", model="facebook/seamless-m4t-v2-large")
+
+# Streamlit title and instructions
+st.title("Real-Time Speech Recognition")
+st.write("Click the button below to start recording and transcribe the audio.")
+
+# Audio recording
+audio_file = st.file_uploader("Upload an audio file", type=["wav", "mp3"])
+
+if audio_file is not None:
+    # Read the audio file and transcribe
+    audio_bytes = audio_file.read()
+    audio_data, samplerate = sf.read(io.BytesIO(audio_bytes))
+
+    # Run the transcription pipeline
+    result = pipe(audio_data)
+
+    # Display the transcription result
+    st.write("Transcription: ", result['text'])