darker model name text

src-tauri/src/transcription.rs

@@ -43,16 +43,19 @@ pub fn transcribe_audio(
         args.push(lang);
     }
 
-    // Run Python script
+    // Run Python script with timeout
     let output = Command::new(python_exe)
         .args(&args)
         .env("PYTHONPATH", crate::paths::project_root().join(".venv312").join("lib").join("python3.12").join("site-packages"))
         .output()
         .map_err(|e| format!("Failed to run Python script: {}", e))?;
 
+    // Check for timeout or other errors
     if !output.status.success() {
         let stderr = String::from_utf8_lossy(&output.stderr);
-        return Err(format!("Python script failed: {}", stderr));
+        let stdout = String::from_utf8_lossy(&output.stdout);
+        return Err(format!("Python script failed: {}\nStdout: {}\nStderr: {}", 
+            output.status, stdout, stderr));
     }
 
     // Parse JSON output

transcribe.py

@@ -21,6 +21,13 @@ def main():
     model_name = sys.argv[2]
     language = sys.argv[3] if len(sys.argv) > 3 else None
 
+    # Check file size - warn for very large files
+    import os
+    file_size_mb = os.path.getsize(audio_file) / (1024 * 1024)
+    if file_size_mb > 100:  # Warn for files over 100MB
+        print(f"Warning: Large file detected ({file_size_mb:.1f}MB). Transcription may take a long time.", file=sys.stderr)
+        print("Consider splitting long audio files into smaller segments for faster processing.", file=sys.stderr)
+
     # Extract audio to temp WAV if needed
     with tempfile.NamedTemporaryFile(suffix='.wav', delete=False) as tmp:
         wav_path = tmp.name
@@ -40,7 +47,9 @@ def main():
 
         model = WhisperModel(model_name, device=device, compute_type=compute_type)
 
-        # Transcribe
+        # Transcribe with progress reporting
+        print(f"Starting transcription of {wav_path} with model {model_name}", file=sys.stderr)
+        
         segments, info = model.transcribe(
             wav_path,
             language=language,
@@ -50,6 +59,8 @@ def main():
             vad_parameters=dict(threshold=0.5, min_speech_duration_ms=250),
             without_timestamps=False
         )
+        
+        print(f"Transcription completed. Detected language: {info.language}", file=sys.stderr)
 
         # Convert to our format
         words = []