Update app.py

app.py

@@ -1,46 +1,48 @@
 from faster_whisper import WhisperModel
 import streamlit as st
-from translator import translate  
+import time
+
+# Load the model
 model_size = "metame/faster-distil-whisper-large-v2"
 model = WhisperModel(model_size, device="cpu", compute_type="int8")
-st.title("Audio to Text Translator")
+
+# Streamlit UI
+st.title("Audio to Text")
 audio_file = st.file_uploader("Upload an audio file", type=["mp3", "wav", "ogg", "flac"])
-languages = {
-    "English": "eng_Latn",
-    "Japanese": "jpn_Jpan",
-    "Hindi": "hin_Deva",
-    "French": "fra_Latn",
-    "Spanish": "spa_Latn",
-    "Chinese": "zho_Hans",
-    "Italian": "ita_Latn",
-    "German": "deu_Latn",
-    "Russian": "rus_Cyrl"
-}
-selected_language = st.selectbox("Select Target Language", list(languages.keys()))
-if st.button("Transcribe and Translate"):
+
+if st.button("Transcribe"):
     if audio_file is not None:
-        with open("temp_audio.mp3", "wb") as f:
+        # Save the audio file
+        audio_path = "temp_audio." + audio_file.name.split('.')[-1]
+        with open(audio_path, "wb") as f:
             f.write(audio_file.getbuffer())
-        segments, info = model.transcribe("temp_audio.mp3", beam_size=5)
-        st.write("Detected language '%s' with probability %f" % (info.language, info.language_probability))
-        col1, col2 = st.columns(2)
-
-        with col1:
-            st.subheader("Transcription")
-
-        with col2:
-            st.subheader("Translation")
-
-        # Process each segment individually
-        for segment in segments:
-            # Translate the segment text
-            translated_text = translate(segment.text, tgt_lang=languages[selected_language])
-            
-            with col1:
-                st.markdown(f"**[{segment.start:.2f}s - {segment.end:.2f}s]** {segment.text}")
-            
-            with col2:
-                st.markdown(f"**[{segment.start:.2f}s - {segment.end:.2f}s]** {translated_text}")
+
+        try:
+            # Start transcription process
+            start_time = time.time()
+            segments, info = model.transcribe(audio_path, beam_size=5)
+
+            # Accumulate transcription results
+            transcription = ""
+            for segment in segments:
+                transcription += f"**[{segment.start:.2f}s - {segment.end:.2f}s]** {segment.text}\n"
+
+            processing_time = time.time() - start_time
+
+            # Display results
+            if transcription:
+                st.write("Detected language: '{}' with probability {:.2f}".format(info.language, info.language_probability))
+                st.subheader("Transcription")
+                st.write(transcription)
+                st.subheader("Processing Time")
+                st.markdown(f"**{processing_time:.2f} seconds**")
+            else:
+                st.error("No transcription was produced. Please check the audio file and try again.")
+
+        except Exception as e:
+            st.error(f"An error occurred during transcription: {e}")
     else:
         st.error("Please upload an audio file.")
 
+
+