Update src/streamlit_app.py

src/streamlit_app.py

@@ -37,4 +37,58 @@ st.altair_chart(alt.Chart(df, height=700, width=700)
         y=alt.Y("y", axis=None),
         color=alt.Color("idx", legend=None, scale=alt.Scale()),
         size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+
+        
+    ))
+
+
+# import streamlit as st
+# import whisper
+# import tempfile
+# import os
+# import torchaudio
+
+# # Title and description
+# st.title("🎧 Whisper Audio Transcriber")
+# st.markdown("Upload a `.wav` or `.mp3` file to get transcribed text with timestamps using Whisper.")
+
+# # Load Whisper model
+# @st.cache_resource
+# def load_model():
+#     return whisper.load_model("base")
+
+# model = load_model()
+# st.success("✅ Whisper model loaded!")
+
+# # File uploader
+# audio_file = st.file_uploader("Upload audio file", type=["wav", "mp3"])
+
+# if audio_file is not None:
+#     # Save uploaded file temporarily
+#     with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp_file:
+#         tmp_file.write(audio_file.read())
+#         temp_path = tmp_file.name
+
+#     # Convert MP3 to WAV if needed
+#     if audio_file.name.endswith(".mp3"):
+#         waveform, sample_rate = torchaudio.load(temp_path)
+#         wav_path = temp_path.replace(".wav", "_converted.wav")
+#         torchaudio.save(wav_path, waveform, sample_rate)
+#         os.remove(temp_path)
+#         temp_path = wav_path
+
+#     # Transcription
+#     st.info("📝 Transcribing...")
+#     result = model.transcribe(temp_path)
+
+#     # Display segments
+#     st.subheader("🕒 Segments with Timestamps")
+#     for segment in result["segments"]:
+#         st.markdown(f"**[{segment['start']:.2f}s - {segment['end']:.2f}s]**: {segment['text']}")
+
+#     # Full transcription
+#     st.subheader("🧾 Full Transcript")
+#     st.text_area("Transcribed Text", result["text"], height=250)
+
+#     # Clean up
+#     os.remove(temp_path)