feat: add detailed logging for Whisper model and processing time

- Log model name explicitly when loading and transcribing
- Log model load time
- Log transcription processing time
- Helps verify correct model is being used

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

backend/app/services/whisper_service.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import time
 from dataclasses import dataclass
 
 from faster_whisper import WhisperModel
@@ -62,14 +63,16 @@ class WhisperService:
     def model(self) -> WhisperModel:
         """Lazy-load Whisper model on first use."""
         if self._model is None:
-            logger.info(f"Loading Whisper model: {self._model_name}")
+            logger.info(f"Loading Whisper model '{self._model_name}' (device=cpu, compute_type=int8)...")
+            load_start = time.time()
             self._model = WhisperModel(
                 self._model_name,
                 device="cpu",
                 compute_type="int8",  # Quantized for faster CPU inference
                 cpu_threads=4
             )
-            logger.info("Whisper model loaded successfully")
+            load_time = time.time() - load_start
+            logger.info(f"Whisper model '{self._model_name}' loaded successfully in {load_time:.2f}s")
         return self._model
 
     def transcribe_audio(self, audio_path: str) -> list[WordTimestamp]:
@@ -82,7 +85,8 @@ class WhisperService:
         Returns:
             List of WordTimestamp objects with word-level timing
         """
-        logger.info(f"Starting Whisper transcription: {audio_path}")
+        logger.info(f"Starting Whisper transcription using model '{self._model_name}': {audio_path}")
+        transcribe_start = time.time()
 
         segments, info = self.model.transcribe(
             audio_path,
@@ -104,7 +108,11 @@ class WhisperService:
                         end=word.end
                     ))
 
-        logger.info(f"Whisper transcription complete: {len(words)} words detected")
+        transcribe_time = time.time() - transcribe_start
+        logger.info(
+            f"Whisper transcription complete using model '{self._model_name}': "
+            f"{len(words)} words detected in {transcribe_time:.2f}s"
+        )
         return words
 
     def identify_speech_gaps(self, words: list[WordTimestamp]) -> list[SpeechGap]: