Silence removal from audio file (.sph to .wav conversion) and segment the file in equal duration

silence_remove_segment.py

# author: github.com/zabir-nabil

import librosa
from pydub import AudioSegment
import pydub
import os

def segment_aud_eq(audio_segment, k):
    # k denotes, seconds * 1000
    a_segs = [audio_segment[i*k:min((i+1)*k, len(audio_segment)-1)] for i in range(len(audio_segment)//k)]
    return a_segs

def silence_remove_segment(filename, silence_thresh=-60., segment_size = 8.0, save = False, save_path = "", ret = True):
    # takes an wav/sph file/anything that librosa supports
    # removes the silence with a threshold
    # makes a list of segment of size >= segment_size (in sec.) 
    # saves the wav file or returns a numpy array 16 bit PCM
    y, sr = librosa.load(filename)
    # convert from float to uint16
    y = np.array(y * (1<<15), dtype=np.int16)
    audio_segment = pydub.AudioSegment(
        y.tobytes(), 
        frame_rate=sr,
        sample_width=y.dtype.itemsize, 
        channels=1
    )
    aud_segs = pydub.silence.split_on_silence(audio_segment, silence_thresh=silence_thresh)
    # join all
    all_seg = sum(aud_segs)
    eq_segs = segment_aud_eq(all_seg, int(segment_size * 1000)) # 1000 because, in AudioSegment 1s is 1000 points

    if save:
        # save as wav
        bn = os.path.basename(filename)
        for i, s in enumerate(eq_segs):
            s.export(f"{os.path.join(save_path, bn.split('.')[0])}_{i}.wav", format="wav")

    if ret:
        return np.array([s.get_array_of_samples() for s in eq_segs], dtype = np.int16)

# usage
sigs = silence_remove_segment("drive/MyDrive/test.sph", save = True)
print(sigs.shape)
print(sigs)

"""
(7, 176400)
[[   7    9    8 ...   62    3  -53]
 [ -86  -85  -51 ...  131   23  -92]
 [-194 -262 -286 ...   58  666  912]
 ...
 [   7    7    8 ... 1044  876  538]
 [ 112 -303 -630 ...  748  619  481]
 [ 360  273  223 ... -145 -625 -936]]
"""