Update utils.py

utils.py

@@ -7,16 +7,23 @@ import subprocess
 # Load Whisper model
 model = whisper.load_model("base")
 
-def process_video(video_file, language):
-    # Save uploaded video to a temp
+def process_video(video_path, language):  # Accept file path, not file object
+    output_video_path = os.path.join(tempfile.gettempdir(), "converted_video.mp4")
+    srt_path = os.path.join(tempfile.gettempdir(), "subtitles.srt")
 
-        # Convert the video to MP4 using ffmpeg
+    try:
+        # Convert video to MP4 using ffmpeg
         print("Converting video to MP4...")
-        subprocess.run(["ffmpeg", "-i", video_path, "-c:v", "libx264", "-preset", "fast", output_video_path], check=True)
-        print(f"Video converted and saved to {output_video_path}")
+        subprocess.run(
+            ["ffmpeg", "-i", video_path, "-c:v", "libx264", "-preset", "fast", output_video_path],
+            check=True,  # Raise error if ffmpeg fails
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE
+        )
+        print("Video converted successfully!")
 
-        # Transcribe the video
-        print("Transcribing video to English...")
+        # Transcribe video
+        print("Transcribing video...")
         result = model.transcribe(output_video_path, language="en")
         print("Transcription completed!")
 
@@ -25,7 +32,6 @@ def process_video(video_file, language):
         if language == "English":
             segments = result["segments"]
         else:
-            # Define translation models
             model_map = {
                 "Hindi": "Helsinki-NLP/opus-mt-en-hi",
                 "Spanish": "Helsinki-NLP/opus-mt-en-es",
@@ -42,12 +48,11 @@ def process_video(video_file, language):
             if not model_name:
                 return f"Unsupported language: {language}"
 
-            print(f"Loading translation model for {language}: {model_name}")
+            print(f"Loading translation model: {model_name}")
             if language == "Telugu":
                 tokenizer = AutoTokenizer.from_pretrained(model_name)
                 translation_model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
                 tgt_lang = "tel_Telu"
-                print(f"Translating to Telugu using NLLB-200 Distilled...")
                 for segment in result["segments"]:
                     inputs = tokenizer(segment["text"], return_tensors="pt", padding=True)
                     translated_tokens = translation_model.generate(
@@ -58,7 +63,6 @@ def process_video(video_file, language):
             else:
                 tokenizer = MarianTokenizer.from_pretrained(model_name)
                 translation_model = MarianMTModel.from_pretrained(model_name)
-                print(f"Translating to {language}...")
                 for segment in result["segments"]:
                     inputs = tokenizer(segment["text"], return_tensors="pt", padding=True)
                     translated = translation_model.generate(**inputs)
@@ -66,8 +70,6 @@ def process_video(video_file, language):
                     segments.append({"text": translated_text, "start": segment["start"], "end": segment["end"]})
 
         # Create SRT file
-        srt_path = os.path.join(tempfile.gettempdir(), "subtitles.srt")
-        print(f"Creating SRT file at {srt_path}")
         with open(srt_path, "w", encoding="utf-8") as f:
             for i, segment in enumerate(segments, 1):
                 start = f"{segment['start']:.3f}".replace(".", ",")
@@ -78,13 +80,14 @@ def process_video(video_file, language):
         return srt_path
 
     except subprocess.CalledProcessError as e:
-        return f"FFmpeg Error: {str(e)}"
+        print(f"FFmpeg Error: {e.stderr.decode()}")
+        return None
     except Exception as e:
-        return f"Unexpected Error: {str(e)}"
+        print(f"Unexpected Error: {str(e)}")
+        return None
     finally:
         # Clean up temporary files
-        print("Cleaning up temporary files...")
-        if os.path.exists(video_path):
-            os.remove(video_path)
         if os.path.exists(output_video_path):
-            os.remove(output_video_path)
+            os.remove(output_video_path)
+        if os.path.exists(video_path):
+            os.remove(video_path)