[Python] .WAV Audio Produced by PyDub AudioSegment.split_on_silence() has no RIFF ID when...

I am currently taking a large audio file and splitting it based on silence using PyDub's split_on_silence function. However, when I go to open this file using wave.open I get an error saying the .wav file has no RIFF id. The source file I am using is a .wav already with a sample rate of 16000 khz. The source file IS readable via wave.open without issue. The issue just arises on the chunk files I create via split_on_silence().

I am able to open the audio chunk in a media player and listen to it without problem. Here is my code and error output:

import numpy as np
import pandas as pd
import shutil

from typing import Union
from pathlib import Path
from pydub import AudioSegment, effects
from pydub.silence import split_on_silence

def split_audio(audio_file_path: Union[Path, str], split_audio_output_dir: Union[Path, str]):

audio_file_name = Path(audio_file_path).name
chunks_output_path = Path(split_audio_output_dir).joinpath(audio_file_name)

if Path(chunks_output_path).is_dir(): # if it is already a path, clear it and recreate it
shutil.rmtree(chunks_output_path)
Path(chunks_output_path).mkdir()
else:
Path(chunks_output_path).mkdir()

sound = AudioSegment.from_wav(audio_file_path)
dBFS = sound.dBFS # get decibels relative to full scale


sound_chunks = split_on_silence(sound,
min_silence_len = 400, # measured in ms
silence_thresh = dBFS -30 # if DBFS goes 30 below the files standard dBFS it will be "silence"
# keep_silence = 500 # keeps silence of 250ms at beginning and end of audio to prevent abrupt start/stop of audio
)

for i, chunk in enumerate(sound_chunks):

silence_chunk = AudioSegment.silent(duration = 1500, frame_rate = 16000) # 1.5 seconds of silence appended to beginning and end of audio chunk
chunk = silence_chunk + chunk + silence_chunk

chunk_normalized = effects.normalize(chunk)
print("Exporting audio chunk {0}.wav for parent file {audio_file_name}".format(i, audio_file_name = audio_file_name))
chunk_normalized.export(chunks_output_path.joinpath("audio_segment_{0}.wav".format(i)))


Now when I go to read one of these audio files I get the following error:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import os
import wave
# load the .wav audio signal
audio_signal = wave.open(r"C:\src\audio_processing\data\processed\split_audio\convertedN216MS_KLGB-Twr-Apr-15-2020-0200Z_Final.mp3.wav\audio_segment_2.wav", 'rb')
sample_rate = audio_signal.getframerate()
audio_len = audio_signal.getnframes() * (1 / sample_rate)

audio_buffer = np.frombuffer(audio_signal.readframes(audio_signal.getnframes()), np.int16)

time = np.linspace(0, audio_len, num = len(audio_buffer))

print("This file has {} audio channel(s)".format(audio_signal.getnchannels()))

# Plot
plt.figure(1)
plt.title("Audio file")
plt.plot(time, audio_buffer)
plt.show()

---------------------------------------------------------------------------
Error Traceback (most recent call last)
<ipython-input-23-9b03ea721d99> in <module>
3
4 # load the .wav audio signal
----> 5 audio_signal = wave.open(r"C:\src\audio_processing\data\processed\split_audio\convertedN216MS_KLGB-Twr-Apr-15-2020-0200Z_Final.mp3.wav\audio_segment_2.wav", 'rb')
6 sample_rate = audio_signal.getframerate()
7 audio_len = audio_signal.getnframes() * (1 / sample_rate)

C:\Python\python37\lib\wave.py in open(f, mode)
508 mode = 'rb'
509 if mode in ('r', 'rb'):
--> 510 return Wave_read(f)
511 elif mode in ('w', 'wb'):
512 return Wave_write(f)

C:\Python\python37\lib\wave.py in __init__(self, f)
162 # else, assume it is an open file object already
163 try:
--> 164 self.initfp(f)
165 except:
166 if self._i_opened_the_file:

C:\Python\python37\lib\wave.py in initfp(self, file)
129 self._file = Chunk(file, bigendian = 0)
130 if self._file.getname() != b'RIFF':
--> 131 raise Error('file does not start with RIFF id')
132 if self._file.read(4) != b'WAVE':
133 raise Error('not a WAVE file')

Error: file does not start with RIFF id

Continue reading...