help me improve the speed and performance of this and write out the full optimization…
- User
help me improve the speed and performance of this and write out the full optimization and wihout using pydub:
async def generate_audio(clenedUpResponse, check_weight): global TASK_STATUS
if "." in clenedUpResponse: clenedUpResponse = clenedUpResponse.replace(".", " komma ") print(clenedUpResponse) print(type(clenedUpResponse)) combined_audio_seg = AudioSegment.empty() # Generate and concatenate audio for each word audio_seg = AudioSegment.from_mp3(f"Audio/{check_weight}.mp3") combined_audio_seg += audio_seg clenedUpResponse = clenedUpResponse.replace('"', "") try: for text in clenedUpResponse.split(): if text != "komma" and len(text) > 2 and text != "hundra": # making sure that text can never be 3 digits so formats it to 2 digits text = text[:2] if text.startswith("0") and len(text) > 1 and text[1:].isdigit(): # Loop through each character in "text" for extra in text: audio_filename = f"Audio/{extra}.mp3" audio_seg = AudioSegment.from_mp3(audio_filename) combined_audio_seg += audio_seg else: audio_filename = f"Audio/{text}.mp3" audio_seg = AudioSegment.from_mp3(audio_filename) combined_audio_seg += audio_seg except Exception as e: print(e) # Export the combined audio file audio_seg = AudioSegment.from_mp3("Audio/kilo.mp3") combined_audio_seg += audio_seg combined_audio_filename = "audio.mp3" combined_audio_seg.export(combined_audio_filename, format="mp3") # Read the audio file and encode it to Base64 with open(combined_audio_filename, "rb") as audio_file: encoded_audio = base64.b64encode(audio_file.read()).decode() # Return the Base64 string as part of a response return {"audio": encoded_audio} - Assistant
As per your request of not using
pydub, I would recommend using thesimpleaudiolibrary for generating and playing audio with native support for .wav files as it offers lower-level control and better performance. Thewavemodule from Python's Standard Library can handle basic operations with .wav files.Below is the revised code. This code will read the .wav files directly, concatenate the waveform data, and then write the resulting waveform data back to file. Please note that the code assumes that the .wav files have the same parameters (sample width, frame rate, and channels).
import wave import contextlib import base64 # This function reads a wave file and returns its parameters and frames def read_wave_file(filename): with wave.open(filename, 'rb') as wave_file: params = wave_file.getparams() frames = wave_file.readframes(params.nframes) return params, frames # This function writes the concatenated wave frames into a new file def write_wave_file(filename, params, frames): with wave.open(filename, 'wb') as wave_file: wave_file.setparams(params) wave_file.writeframes(frames) async def generate_audio(cleaned_up_response, check_weight): global TASK_STATUS cleaned_up_response = cleaned_up_response.replace(".", " komma ") cleaned_up_response = cleaned_up_response.replace('"', "") combined_frames = b'' # Keeping the wave params consistent across all the files wave_params = None # Sound for "check_weight" weight_params, weight_frames = read_wave_file(f"Audio/{check_weight}.wav") combined_frames += weight_frames try: for text in cleaned_up_response.split(): if text != "komma" and len(text) > 2 and text != "hundra": # Truncate the text to 2 digits text = text[:2] if text.startswith("0") and len(text) > 1 and text[1:].isdigit(): # Read each character audio file and append the frames for extra in text: extra_params, extra_frames = read_wave_file(f"Audio/{extra}.wav") combined_frames += extra_frames else: # Same for normal text audio files text_params, text_frames = read_wave_file(f"Audio/{text}.wav") combined_frames += text_frames # Just to ensure all files have the same params if wave_params is None: wave_params = text_params except Exception as e: print(e) return None # Add the "kilo" word sound at the end kilo_params, kilo_frames = read_wave_file("Audio/kilo.wav") combined_frames += kilo_frames # Now write the combined audio to a file combined_audio_filename = "audio.wav" write_wave_file(combined_audio_filename, wave_params, combined_frames) # Read the audio file and encode it to Base64 with open(combined_audio_filename, "rb") as audio_file: encoded_audio = base64.b64encode(audio_file.read()).decode() # Return the Base64 string as part of a response return {"audio": encoded_audio}Please make sure that you have all your audio files converted to the .wav format. Conversion can be done with a variety of tools outside Python.
You also need to make sure that all the files have the same parameters (channels, bit rate, frame rate) for direct waveform concatenation to work.
To improve the performance even more, you could look into using an asynchronous library for file I/O like
aiofiles, though for CPU-bound tasks like audio processing, the main bottleneck is rarely I/O.