python - Pydub - 将 split_on_silence 与最小长度/文件大小相结合

Question

我有两个脚本，其中一个会分割一定长度的音频，另一个会在每次有无声段落时分割音频。是否可以在静音时拆分音频，但只有在经过一定时间后才能拆分音频？我需要不少于 5 分钟的无声分割视频。

忽略静音的拆分脚本:

from pydub import AudioSegment
#from pydub.utils import mediainfo
from pydub.utils import make_chunks
import math

#lac_audio = AudioSegment.from_file("Kalimba.mp3", "mp3")
#flac_audio.export("audio.mp3", format="mp3")
myaudio = AudioSegment.from_file("Kalimba.mp3" , "mp3")
channel_count = myaudio.channels    #Get channels
sample_width = myaudio.sample_width #Get sample width
duration_in_sec = len(myaudio) / 1000#Length of audio in sec
sample_rate = myaudio.frame_rate

print "sample_width=", sample_width 
print "channel_count=", channel_count
print "duration_in_sec=", duration_in_sec 
print "frame_rate=", sample_rate
bit_rate =16  #assumption , you can extract from mediainfo("test.wav") dynamically


wav_file_size = (sample_rate * bit_rate * channel_count * duration_in_sec) / 8
print "wav_file_size = ",wav_file_size


file_split_size = 10000000  # 10Mb OR 10, 000, 000 bytes
total_chunks =  wav_file_size // file_split_size

#Get chunk size by following method #There are more than one ofcourse
#for  duration_in_sec (X) -->  wav_file_size (Y)
#So   whats duration in sec  (K) --> for file size of 10Mb
#  K = X * 10Mb / Y

chunk_length_in_sec = math.ceil((duration_in_sec * 10000000 ) /wav_file_size)   #in sec
chunk_length_ms = chunk_length_in_sec * 1000
chunks = make_chunks(myaudio, chunk_length_ms)

#Export all of the individual chunks as wav files

for i, chunk in enumerate(chunks):
    chunk_name = "chunk{0}.mp3".format(i)
    print "exporting", chunk_name
    chunk.export(chunk_name, format="mp3")

忽略长度的分割脚本:

from pydub import AudioSegment
from pydub.silence import split_on_silence

sound = AudioSegment.from_mp3("my_file.mp3")
chunks = split_on_silence(sound, 
    # must be silent for at least half a second
    min_silence_len=500,

    # consider it silent if quieter than -16 dBFS
    silence_thresh=-16

 )

for i, chunk in enumerate(chunks):
    chunk.export("/path/to/ouput/dir/chunk{0}.wav".format(i), format="wav")

Answer 1

我的建议是使用 pydub.silence.split_on_silence()然后根据需要重新组合这些片段，以便您拥有与目标大小大致相同的文件。

有点像

from pydub import AudioSegment
from pydub.silence import split_on_silence

sound = AudioSegment.from_file("/path/to/file.mp3", format="mp3")
chunks = split_on_silence(
    sound,

    # split on silences longer than 1000ms (1 sec)
    min_silence_len=1000,

    # anything under -16 dBFS is considered silence
    silence_thresh=-16, 

    # keep 200 ms of leading/trailing silence
    keep_silence=200
)

# now recombine the chunks so that the parts are at least 90 sec long
target_length = 90 * 1000
output_chunks = [chunks[0]]
for chunk in chunks[1:]:
    if len(output_chunks[-1]) < target_length:
        output_chunks[-1] += chunk
    else:
        # if the last output chunk is longer than the target length,
        # we can start a new one
        output_chunks.append(chunk)

# now your have chunks that are bigger than 90 seconds (except, possibly the last one)

或者，您可以使用 pydub.silence.detect_nonsilent()找到范围并自行决定在何处分割原始音频

注意:我还在 similar/duplicate github issue 上发布了这个