feat: add transcript download, history list, and UI changes

app/history.py

@@ -2,6 +2,7 @@ import json
 import os
 import datetime
 import csv
+import tempfile
 
 HISTORY_FILE = "data/history.json"
 
@@ -31,6 +32,30 @@ def save_to_history(audio_filepath: str, transcript: str, language: str):
     with open(HISTORY_FILE, "w") as f:
         json.dump(history, f, indent=4)
 
+def get_history() -> list:
+    """
+    Returns the list of past transcriptions for display in the UI.
+    Returns newest entries first.
+    """
+    if not os.path.exists(HISTORY_FILE):
+        return []
+    try:
+        with open(HISTORY_FILE, "r") as f:
+            history = json.load(f)
+        return list(reversed(history))
+    except Exception:
+        return []
+
+def save_transcript_as_txt(transcript: str) -> str:
+    """
+    Saves a single transcript string to a temp .txt file and returns the path.
+    Used for the per-transcription download button.
+    """
+    tmp = tempfile.NamedTemporaryFile(delete=False, suffix=".txt", mode="w", encoding="utf-8")
+    tmp.write(transcript)
+    tmp.close()
+    return tmp.name
+
 def export_history(format: str = "csv"):
     """
     Exports the saved history into a downloadable format.

gradio_ui.py

@@ -1,68 +1,102 @@
 import gradio as gr
 from app.asr_model import load_model, transcribe_audio
 from app.language_detection import detect_language_from_text
-from app.history import save_to_history, export_history
+from app.history import save_to_history, export_history, get_history, save_transcript_as_txt
+import pandas as pd
 
 def process_audio(audio_path):
     if audio_path is None:
-        return "No audio uploaded.", "Unknown"
-        
+        return "No audio uploaded.", "Unknown", None
+
     print(f"\n--- New Request ---")
     print(f"Processing audio: {audio_path}")
-    
-    # Transcribe Speech
-    print("Transcribing... (If this is the first time, it is downloading a 400MB model)")
+
+    print("Transcribing...")
     transcript = transcribe_audio(audio_path)
-    print(f"Transcription complete: {transcript[:50]}...")
-    
-    # Detect Language from transcript
+    print(f"Transcription complete: {transcript[:80]}")
+
     print("Detecting language...")
     lang = detect_language_from_text(transcript)
-    
-    # Save History
+
     print("Saving to history...")
     save_to_history(audio_path, transcript, lang)
-    
+
+    # Create a downloadable .txt file for the transcript
+    txt_path = save_transcript_as_txt(transcript)
+
     print("Done!\n")
-    return transcript, lang
+    return transcript, lang, txt_path
 
 def export_history_wrapper():
     path = export_history("csv")
     return path if path else None
 
+def load_history_table():
+    """Load history and return as a list of lists for gr.Dataframe."""
+    history = get_history()
+    if not history:
+        return []
+    rows = []
+    for entry in history:
+        rows.append([
+            entry.get("timestamp", "")[:19].replace("T", " "),
+            entry.get("audio_file", ""),
+            entry.get("language", ""),
+            entry.get("transcript", "")
+        ])
+    return rows
+
 def create_ui():
     with gr.Blocks(title="Multilingual ASR") as demo:
-        gr.Markdown("# Multilingual Automatic Speech Recognition")
-        
+        gr.Markdown("# 🎙️ Multilingual Automatic Speech Recognition")
+
         with gr.Tabs():
-            with gr.TabItem("Transcribe"):
+            with gr.TabItem("📝 Transcribe"):
                 gr.Markdown("Upload an audio file to get a text transcription using Wav2Vec.")
-                
+
                 with gr.Row():
                     with gr.Column():
                         audio_input = gr.Audio(type="filepath", label="Upload Audio")
                         transcribe_btn = gr.Button("Transcribe", variant="primary")
-                        
+
                     with gr.Column():
                         lang_output = gr.Textbox(label="Detected Language")
                         transcript_output = gr.Textbox(label="Transcription", lines=10)
-                        
+                        download_txt = gr.File(label="⬇️ Download Transcript (.txt)", visible=False)
+
                 transcribe_btn.click(
                     fn=process_audio,
                     inputs=audio_input,
-                    outputs=[transcript_output, lang_output]
+                    outputs=[transcript_output, lang_output, download_txt]
+                ).then(
+                    fn=lambda path: gr.File(value=path, visible=path is not None),
+                    inputs=download_txt,
+                    outputs=download_txt
                 )
-                
-            with gr.TabItem("History"):
-                gr.Markdown("Download your past transcriptions.")
-                download_btn = gr.Button("Prepare History for Download")
-                file_output = gr.File(label="Download CSV")
-                
-                download_btn.click(
-                    fn=export_history_wrapper,
-                    outputs=file_output
+
+            with gr.TabItem("📋 History"):
+                gr.Markdown("Your past transcriptions (newest first).")
+
+                with gr.Row():
+                    refresh_btn = gr.Button("🔄 Refresh History")
+                    export_btn = gr.Button("⬇️ Export as CSV")
+
+                history_table = gr.Dataframe(
+                    headers=["Timestamp", "Audio File", "Language", "Transcript"],
+                    datatype=["str", "str", "str", "str"],
+                    value=load_history_table,
+                    wrap=True,
+                    label="Transcription History"
+                )
+                csv_file_output = gr.File(label="Download CSV", visible=False)
+
+                refresh_btn.click(fn=load_history_table, outputs=history_table)
+                export_btn.click(fn=export_history_wrapper, outputs=csv_file_output).then(
+                    fn=lambda path: gr.File(value=path, visible=path is not None),
+                    inputs=csv_file_output,
+                    outputs=csv_file_output
                 )
-                
+
     return demo
 
 if __name__ == "__main__":