Basic App.py

app.py

@@ -0,0 +1,51 @@
+import torchaudio as ta
+import streamlit as st
+
+from io import BytesIO
+from transformers import AutoProcessor, SeamlessM4TModel
+
+processor = AutoProcessor.from_pretrained("facebook/hf-seamless-m4t-medium", use_fast=False)
+model = SeamlessM4TModel.from_pretrained("facebook/hf-seamless-m4t-medium")
+
+# Title of the app
+st.title("Audio Player with Live Transcription")
+
+# Sidebar for file uploader and submit button
+st.sidebar.header("Upload Audio Files")
+uploaded_files = st.sidebar.file_uploader("Choose audio files", type=["mp3", "wav"], accept_multiple_files=True)
+submit_button = st.sidebar.button("Submit")
+
+
+# def transcribe_audio(audio_data):
+#     recognizer = sr.Recognizer()
+#     with sr.AudioFile(audio_data) as source:
+#         audio = recognizer.record(source)
+#     try:
+#         # Transcribe the audio using Google Web Speech API
+#         transcription = recognizer.recognize_google(audio)
+#         return transcription
+#     except sr.UnknownValueError:
+#         return "Unable to transcribe the audio."
+#     except sr.RequestError as e:
+#         return f"Could not request results; {e}"
+
+
+if submit_button and uploaded_files:
+    st.write("Files uploaded successfully!")
+
+    for uploaded_file in uploaded_files:
+        # Display file name and audio player
+        print(uploaded_file)
+        st.write(f"**File name**: {uploaded_file.name}")
+        st.audio(uploaded_file, format=uploaded_file.type)
+
+        # Transcription section
+        st.write("**Transcription**:")
+
+        # Read the uploaded file data
+        waveform, sampling_rate = ta.load(uploaded_file.getvalue())
+
+        # Run transcription function and display
+        # import pdb;pdb.set_trace()
+        # st.write(audio_data.getvalue())
+