feat: use whisperx to allow diarization

main.py

@@ -26,15 +26,19 @@ def record_audio():
 def transcribe_audio():
     print("🔠 Transcribing with WhisperX...")
     subprocess.run([
-        # "pipenv run python3 -m whisperx",
-        "whisper",
+        "uvx",
+        "whisperx",
         MEETING_FILE,
         "--device", "cpu",  # Use CPU
         "--language", "en",
-        # "--diarize", Put back when whisperX works.
+        # Uncomment the next line to enable diarization, requires you to download the model from Hugging Face.
+        # "--diarize",
+        "--compute_type", "float32",
         "--model", WHISPER_MODEL,
         "--output_format", "json",
         "--output_dir", "."
+        # You should only need to uncomment this once to perform the initial model download.
+        # "--hf_token", "your_huggingface_token_here"
     ], check=True)
 
 def summarize_with_local_model():
@@ -43,7 +47,7 @@ def summarize_with_local_model():
         transcript = json.load(f)
 
     text = "\n".join(
-        seg["text"]
+        f"{seg['speaker']}: {seg['text']}"
         for seg in transcript["segments"]
     )