Update app.py

app.py

@@ -1,37 +1,11 @@
 import gradio as gr
-import requests
-import base64
 import os
-import json
-import numpy as np
-import scipy.io.wavfile as wavfile
-import tempfile
 import torch
-from google import genai
-from google.genai import types
-from gradio_client import Client, handle_file
 from pyannote.audio import Pipeline
 
 # Configuration
-SEAMLESS_SPACE = "tgpro1/sttr"
-GEMINI_API_KEY = os.environ.get('GEMINI_API_KEY')
 HF_TOKEN = os.environ.get('HF_TOKEN')
 
-LANGUAGES = {
-    "Darija": "ar-SA",
-    "Arabic": "ar-SA", 
-    "French": "fr-FR",
-    "English": "en-US",
-    "Spanish": "es-ES",
-    "German": "de-DE",
-    "Italian": "it-IT",
-    "Portuguese": "pt-PT",
-    "Chinese": "zh-CN",
-    "Japanese": "ja-JP",
-    "Korean": "ko-KR",
-    "Russian": "ru-RU",
-}
-
 # Pyannote Diarization
 diarization_pipeline = None
 try:
@@ -50,7 +24,7 @@ except Exception as e:
 
 def diarize_audio(audio_path, min_speakers=1, max_speakers=5):
     if not diarization_pipeline:
-        return {"error": "Diarization not available"}
+        return {"error": "Diarization not available. Check HF_TOKEN."}
     try:
         diarization = diarization_pipeline(audio_path, min_speakers=int(min_speakers), max_speakers=int(max_speakers))
         speakers = []
@@ -60,16 +34,17 @@ def diarize_audio(audio_path, min_speakers=1, max_speakers=5):
     except Exception as e:
         return {"error": str(e)}
 
-with gr.Blocks(title="STTR") as demo:
+with gr.Blocks(title="STTR - Speaker Diarization") as demo:
     gr.Markdown("# STTR - Speaker Diarization")
-    with gr.Tab("Diarization"):
-        audio_in = gr.Audio(type="filepath", label="Audio")
-        with gr.Row():
-            min_spk = gr.Slider(1, 10, value=1, step=1, label="Min Speakers")
-            max_spk = gr.Slider(1, 10, value=5, step=1, label="Max Speakers")
-        btn = gr.Button("Analyze", variant="primary")
-        output = gr.JSON(label="Result")
-        btn.click(diarize_audio, [audio_in, min_spk, max_spk], output, api_name="/diarize")
+    gr.Markdown("### Identify who speaks when (pyannote 3.1)")
+    
+    audio_in = gr.Audio(type="filepath", label="Upload Audio")
+    with gr.Row():
+        min_spk = gr.Slider(1, 10, value=1, step=1, label="Min Speakers")
+        max_spk = gr.Slider(1, 10, value=5, step=1, label="Max Speakers")
+    btn = gr.Button("Analyze Speakers", variant="primary")
+    output = gr.JSON(label="Speaker Segments")
+    btn.click(diarize_audio, [audio_in, min_spk, max_spk], output, api_name="/diarize")
 
 if __name__ == "__main__":
     demo.launch(server_name="0.0.0.0", server_port=int(os.environ.get("PORT", 7860)))