Update README.md

README.md

@@ -1,15 +1,3 @@
----
-title: AI Conversation Sentiment Analyzer
-emoji: 🎙
-colorFrom: blue
-colorTo: purple
-sdk: gradio
-sdk_version: 6.12.0
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
 # 🎙 AI Conversation Sentiment Analyzer
 
 An AI-powered system that transcribes audio, detects speakers, and analyzes sentiment for each utterance.
@@ -50,4 +38,27 @@ An AI-powered system that transcribes audio, detects speakers, and analyzes sent
 
 ---
 
-## 📊 Example Output
+## 📊 Example Output
+
+
+---
+title: AI Conversation Sentiment Analyzer
+emoji: 🎙
+colorFrom: purple
+colorTo: green
+sdk: gradio
+sdk_version: "4.44.0"
+app_file: app.py
+pinned: false
+---
+
+# AI Conversation Sentiment Analyzer
+
+Upload or record audio → get speaker-separated transcription with sentiment labels.
+
+**Models used:**
+- [openai/whisper-base](https://huggingface.co/openai/whisper-base) — transcription
+- [pyannote/speaker-diarization-3.1](https://huggingface.co/pyannote/speaker-diarization-3.1) — speaker diarization
+- [nlptown/bert-base-multilingual-uncased-sentiment](https://huggingface.co/nlptown/bert-base-multilingual-uncased-sentiment) — sentiment analysis
+
+**Required secret:** `HF_TOKEN` (needed to access pyannote models — set under Space Settings → Repository secrets)