added 16k sampling for faster transcription

transcription.py

@@ -69,12 +69,21 @@ class DownloadAudio:
             current_dir = os.getcwd()
             print(current_dir)
             executable_path = os.path.join(current_dir, "exec/yt-dlp_linux")
+            
             # Download the video as an audio file using youtube-dl
-            result = subprocess.run([executable_path, "-x", "--audio-format", "wav", "-o", FINAL_WAV_PATH, self.link])
+            original_download_path = f"{pathname}/audio.wav"
+            result = subprocess.run([executable_path, "-x", "--audio-format", "wav", "-o", original_download_path, self.link])
             if result.returncode != 0:
                 print("Failed to download audio. Retrying...")
                 return "FAILED"
 
+            sound = AudioSegment.from_wav(original_download_path)
+            sound.set_channels(1)
+            sound = sound.set_frame_rate(16000)                
+            sound = sound.set_channels(1)    
+            sound.export(FINAL_WAV_PATH, format="wav")
+            os.remove(original_download_path)
+            
         # Load the input .wav file
         audio = AudioSegment.from_wav(FINAL_WAV_PATH)
     
@@ -86,26 +95,26 @@ class DownloadAudio:
         if total_byte_size < MAX_FILE_SIZE_BYTES:
             return FINAL_WAV_PATH
 
-        # Get the size of the wav file
-        channels = audio.channels
-        sample_width = audio.sample_width
-        duration_in_sec = math.ceil(len(audio) / 1000)
-        sample_rate = audio.frame_rate
-        bit_rate = sample_width * 8
-        wav_file_size = (sample_rate * bit_rate * channels * duration_in_sec) / 8
-
-        # Get the length of each chunk in milliseconds and make the chunks
-        chunk_length_in_sec = math.ceil((duration_in_sec * MAX_FILE_SIZE_BYTES ) / wav_file_size)   #in sec
-        chunk_length_ms = chunk_length_in_sec * 1000
-        chunks = make_chunks(audio, chunk_length_ms)
-
-        # Export all of the individual chunks as wav files
-        chunk_names = []
-        for i, chunk in enumerate(chunks):
-            chunk_name = f"{self.YOUTUBE_VIDEO_ID}_{i}.wav"
-            output_chunk_path = f"{pathname}/{chunk_name}"
-            chunk_names.append(output_chunk_path)
-            chunk.export(f"{output_chunk_path}", format="wav")
+        # # Get the size of the wav file
+        # channels = audio.channels
+        # sample_width = audio.sample_width
+        # duration_in_sec = math.ceil(len(audio) / 1000)
+        # sample_rate = audio.frame_rate
+        # bit_rate = sample_width * 8
+        # wav_file_size = (sample_rate * bit_rate * channels * duration_in_sec) / 8
+
+        # # Get the length of each chunk in milliseconds and make the chunks
+        # chunk_length_in_sec = math.ceil((duration_in_sec * MAX_FILE_SIZE_BYTES ) / wav_file_size)   #in sec
+        # chunk_length_ms = chunk_length_in_sec * 1000
+        # chunks = make_chunks(audio, chunk_length_ms)
+
+        # # Export all of the individual chunks as wav files
+        # chunk_names = []
+        # for i, chunk in enumerate(chunks):
+        #     chunk_name = f"{self.YOUTUBE_VIDEO_ID}_{i}.wav"
+        #     output_chunk_path = f"{pathname}/{chunk_name}"
+        #     chunk_names.append(output_chunk_path)
+        #     chunk.export(f"{output_chunk_path}", format="wav")
         
         return FINAL_WAV_PATH