对音频切分成小音频（机器学习用）

我是把so-vits中小工具分析源码然后提取出来了。以后可以写在自己的程序里。

-------流程这是我做的流程你可以不用看

从开源代码中快速获取自己需要的东西

如果有界面f12看他里面的接口然后在源码中全局搜索没有接口比如socket看他的消息字段然后推测。然后提取补齐代码就行了

-------

你需要看的

提取出来有3个类

run.py是我自己写的

其他是我提取的源码首先你得install一些包

numpy,librosa,soundfile

slicer2.py

import numpy as np


# This function is obtained from librosa.
def get_rms(
    y,
    *,
    frame_length=2048,
    hop_length=512,
    pad_mode="constant",
):
    padding = (int(frame_length // 2), int(frame_length // 2))
    y = np.pad(y, padding, mode=pad_mode)

    axis = -1
    # put our new within-frame axis at the end for now
    out_strides = y.strides + tuple([y.strides[axis]])
    # Reduce the shape on the framing axis
    x_shape_trimmed = list(y.shape)
    x_shape_trimmed[axis] -= frame_length - 1
    out_shape = tuple(x_shape_trimmed) + tuple([frame_length])
    xw = np.lib.stride_tricks.as_strided(
        y, shape=out_shape, strides=out_strides
    )
    if axis < 0:
        target_axis = axis - 1
    else:
        target_axis = axis + 1
    xw = np.moveaxis(xw, -1, target_axis)
    # Downsample along the target axis
    slices = [slice(None)] * xw.ndim
    slices[axis] = slice(0, None, hop_length)
    x = xw[tuple(slices)]

    # Calculate power
    power = np.mean(np.abs(x) ** 2, axis=-2, keepdims=True)

    return np.sqrt(power)


class Slicer:
    def __init__(self,
                 sr: int,
                 threshold: float = -40.,
                 min_length: int = 5000,
                 min_interval: int = 300,
                 hop_size: int = 20,
                 max_sil_kept: int = 5000):
        if not min_length >= min_interval >= hop_size:
            raise ValueError('The following condition must be satisfied: min_length >= min_interval >= hop_size')
        if not max_sil_kept >= hop_size:
            raise ValueError('The following condition must be satisfied: max_sil_kept >= hop_size')
        min_interval = sr * min_interval / 1000
        self.threshold = 10 ** (threshold / 20.)
        self.hop_size = round(sr * hop_size / 1000)
        self.win_size = min(round(min_interval), 4 * self.hop_size)
        self.min_length = round(sr * min_length / 1000 / self.hop_size)
        self.min_interval = round(min_interval / self.hop_size)
        self.max_sil_kept = round(sr * max_sil_kept / 1000 / self.hop_size)

    def _apply_slice(self, waveform, begin, end):
        if len(waveform.shape) > 1:
            return waveform[:, begin * self.hop_size: min(waveform.shape[1], end * self.hop_size)]
        else:
            return waveform[begin * self.hop_size: min(waveform.shape[0], end * self.hop_size)]

    # @timeit
    def slice(self, waveform):
        if len(waveform.shape) > 1:
            samples = waveform.mean(axis=0)
        else:
            samples = waveform
        if samples.shape[0] <= self.min_length:
            return [waveform]
        rms_list = get_rms(y=samples, frame_length=self.win_size, hop_length=self.hop_size).squeeze(0)
        sil_tags = []
        silence_start = None
        clip_start = 0
        for i, rms in enumerate(rms_list):
            # Keep looping while frame is silent.
            if rms < self.threshold:
                # Record start of silent frames.
                if silence_start is None:
                    silence_start = i
                continue
            # Keep looping while frame is not silent and silence start has not been recorded.
            if silence_start is None:
                continue
            # Clear recorded silence start if interval is not enough or clip is too short
            is_leading_silence = silence_start == 0 and i > self.max_sil_kept
            need_slice_middle = i - silence_start >= self.min_interval and i - clip_start >= self.min_length
            if not is_leading_silence and not need_slice_middle:
                silence_start = None
                continue
            # Need slicing. Record the range of silent frames to be removed.
            if i - silence_start <= self.max_sil_kept:
                pos = rms_list[silence_start: i + 1].argmin() + silence_start
                if silence_start == 0:
                    sil_tags.append((0, pos))
                else:
                    sil_tags.append((pos, pos))
                clip_start = pos
            elif i - silence_start <= self.max_sil_kept * 2:
                pos = rms_list[i - self.max_sil_kept: silence_start + self.max_sil_kept + 1].argmin()
                pos += i - self.max_sil_kept
                pos_l = rms_list[silence_start: silence_start + self.max_sil_kept + 1].argmin() + silence_start
                pos_r = rms_list[i - self.max_sil_kept: i + 1].argmin() + i - self.max_sil_kept
                if silence_start == 0:
                    sil_tags.append((0, pos_r))
                    clip_start = pos_r
                else:
                    sil_tags.append((min(pos_l, pos), max(pos_r, pos)))
                    clip_start = max(pos_r, pos)
            else:
                pos_l = rms_list[silence_start: silence_start + self.max_sil_kept + 1].argmin() + silence_start
                pos_r = rms_list[i - self.max_sil_kept: i + 1].argmin() + i - self.max_sil_kept
                if silence_start == 0:
                    sil_tags.append((0, pos_r))
                else:
                    sil_tags.append((pos_l, pos_r))
                clip_start = pos_r
            silence_start = None
        # Deal with trailing silence.
        total_frames = rms_list.shape[0]
        if silence_start is not None and total_frames - silence_start >= self.min_interval:
            silence_end = min(total_frames, silence_start + self.max_sil_kept)
            pos = rms_list[silence_start: silence_end + 1].argmin() + silence_start
            sil_tags.append((pos, total_frames + 1))
        # Apply and return slices.
        if len(sil_tags) == 0:
            return [waveform]
        else:
            chunks = []
            if sil_tags[0][0] > 0:
                chunks.append(self._apply_slice(waveform, 0, sil_tags[0][0]))
            for i in range(len(sil_tags) - 1):
                chunks.append(self._apply_slice(waveform, sil_tags[i][1], sil_tags[i + 1][0]))
            if sil_tags[-1][1] < total_frames:
                chunks.append(self._apply_slice(waveform, sil_tags[-1][1], total_frames))
            return chunks


def main():
    import os.path
    from argparse import ArgumentParser

    import librosa
    import soundfile

    parser = ArgumentParser()
    parser.add_argument('audio', type=str, help='The audio to be sliced')
    parser.add_argument('--out', type=str, help='Output directory of the sliced audio clips')
    parser.add_argument('--db_thresh', type=float, required=False, default=-40,
                        help='The dB threshold for silence detection')
    parser.add_argument('--min_length', type=int, required=False, default=5000,
                        help='The minimum milliseconds required for each sliced audio clip')
    parser.add_argument('--min_interval', type=int, required=False, default=300,
                        help='The minimum milliseconds for a silence part to be sliced')
    parser.add_argument('--hop_size', type=int, required=False, default=10,
                        help='Frame length in milliseconds')
    parser.add_argument('--max_sil_kept', type=int, required=False, default=500,
                        help='The maximum silence length kept around the sliced clip, presented in milliseconds')
    args = parser.parse_args()
    out = args.out
    if out is None:
        out = os.path.dirname(os.path.abspath(args.audio))
    audio, sr = librosa.load(args.audio, sr=None, mono=False)
    slicer = Slicer(
        sr=sr,
        threshold=args.db_thresh,
        min_length=args.min_length,
        min_interval=args.min_interval,
        hop_size=args.hop_size,
        max_sil_kept=args.max_sil_kept
    )
    chunks = slicer.slice(audio)
    if not os.path.exists(out):
        os.makedirs(out)
    for i, chunk in enumerate(chunks):
        if len(chunk.shape) > 1:
            chunk = chunk.T
        soundfile.write(os.path.join(out, f'%s_%d.wav' % (os.path.basename(args.audio).rsplit('.', maxsplit=1)[0], i)), chunk, sr)


if __name__ == '__main__':
    main()

auto_slicer.py

import os
import numpy as np
import librosa
import soundfile as sf
from slicer2 import Slicer

class AutoSlicer:
    def __init__(self):
        self.slicer_params = {
            "threshold": -40,
            "min_length": 5000,
            "min_interval": 300,
            "hop_size": 10,
            "max_sil_kept": 500,
        }
        self.original_min_interval = self.slicer_params["min_interval"]

    def auto_slice(self, filename, input_dir, output_dir, max_sec):
        audio, sr = librosa.load(os.path.join(input_dir, filename), sr=None, mono=False)
        slicer = Slicer(sr=sr, **self.slicer_params)
        chunks = slicer.slice(audio)
        files_to_delete = []
        for i, chunk in enumerate(chunks):
            if len(chunk.shape) > 1:
                chunk = chunk.T
            output_filename = f"{os.path.splitext(filename)[0]}_{i}"
            output_filename = "".join(c for c in output_filename if c.isascii() or c == "_") + ".wav"
            output_filepath = os.path.join(output_dir, output_filename)
            sf.write(output_filepath, chunk, sr)
            #Check and re-slice audio that more than max_sec.
            while True:
                new_audio, sr = librosa.load(output_filepath, sr=None, mono=False)
                if librosa.get_duration(y=new_audio, sr=sr) <= max_sec:
                    break
                self.slicer_params["min_interval"] = self.slicer_params["min_interval"] // 2
                if self.slicer_params["min_interval"] >= self.slicer_params["hop_size"]:
                    new_chunks = Slicer(sr=sr, **self.slicer_params).slice(new_audio)
                    for j, new_chunk in enumerate(new_chunks):
                        if len(new_chunk.shape) > 1:
                            new_chunk = new_chunk.T
                        new_output_filename = f"{os.path.splitext(output_filename)[0]}_{j}.wav"
                        sf.write(os.path.join(output_dir, new_output_filename), new_chunk, sr)
                    files_to_delete.append(output_filepath)
                else:
                    break
            self.slicer_params["min_interval"] = self.original_min_interval
        for file_path in files_to_delete:
            if os.path.exists(file_path):
                os.remove(file_path)

    def merge_short(self, output_dir, max_sec, min_sec):
        short_files = []
        for filename in os.listdir(output_dir):
            filepath = os.path.join(output_dir, filename)
            if filename.endswith(".wav"):
                audio, sr = librosa.load(filepath, sr=None, mono=False)
                duration = librosa.get_duration(y=audio, sr=sr)
                if duration < min_sec:
                    short_files.append((filepath, audio, duration))
        short_files.sort(key=lambda x: x[2], reverse=True)
        merged_audio = []
        current_duration = 0
        for filepath, audio, duration in short_files:
            if current_duration + duration <= max_sec:
                merged_audio.append(audio)
                current_duration += duration
                os.remove(filepath)
            else:
                if merged_audio:
                    output_audio = np.concatenate(merged_audio, axis=-1)
                    if len(output_audio.shape) > 1:
                        output_audio = output_audio.T
                    output_filename = f"merged_{len(os.listdir(output_dir))}.wav"
                    sf.write(os.path.join(output_dir, output_filename), output_audio, sr)
                    merged_audio = [audio]
                    current_duration = duration
                    os.remove(filepath)
        if merged_audio and current_duration >= min_sec:
            output_audio = np.concatenate(merged_audio, axis=-1)
            if len(output_audio.shape) > 1:
                output_audio = output_audio.T
            output_filename = f"merged_{len(os.listdir(output_dir))}.wav"
            sf.write(os.path.join(output_dir, output_filename), output_audio, sr)
    
    def slice_count(self, input_dir, output_dir):
        orig_duration = final_duration = 0
        for file in os.listdir(input_dir):
            if file.endswith(".wav"):
                _audio, _sr = librosa.load(os.path.join(input_dir, file), sr=None, mono=False)
                orig_duration += librosa.get_duration(y=_audio, sr=_sr)
        wav_files = [file for file in os.listdir(output_dir) if file.endswith(".wav")]
        num_files = len(wav_files)
        max_duration = -1
        min_duration = float("inf")
        for file in wav_files:
            file_path = os.path.join(output_dir, file)
            audio, sr = librosa.load(file_path, sr=None, mono=False)
            duration = librosa.get_duration(y=audio, sr=sr)
            final_duration += float(duration)
            if duration > max_duration:
                max_duration = float(duration)
            if duration < min_duration:
                min_duration = float(duration)
        return num_files, max_duration, min_duration, orig_duration, final_duration

run.py

import os
from auto_slicer import AutoSlicer
import librosa
def slicer_fn(input_dir, output_dir, process_method, max_sec, min_sec):
    if output_dir == "":
        return "请先选择输出的文件夹"
    if output_dir == input_dir:
        return "输出目录不能和输入目录相同"
    slicer = AutoSlicer()
    if os.path.exists(output_dir) is not True:
        os.makedirs(output_dir)
    for filename in os.listdir(input_dir):
        if filename.lower().endswith(".wav"):
            slicer.auto_slice(filename, input_dir, output_dir, max_sec)
    if process_method == "丢弃":
        for filename in os.listdir(output_dir):
            if filename.endswith(".wav"):
                filepath = os.path.join(output_dir, filename)
                audio, sr = librosa.load(filepath, sr=None, mono=False)
                if librosa.get_duration(y=audio, sr=sr) < min_sec:
                    os.remove(filepath)
    elif process_method == "将过短音频整合为长音频":
        slicer.merge_short(output_dir, max_sec, min_sec)
    file_count, max_duration, min_duration, orig_duration, final_duration = slicer.slice_count(input_dir, output_dir)
    hrs = int(final_duration / 3600)
    mins = int((final_duration % 3600) / 60)
    sec = format(float(final_duration % 60), '.2f')
    rate = format(100 * (final_duration / orig_duration), '.2f') if orig_duration != 0 else 0
    rate_msg = f"为原始音频时长的{rate}%" if rate != 0 else "因未知问题无法计算切片时长的占比"
    return f"成功将音频切分为{file_count}条片段其中最长{max_duration}秒最短{min_duration}秒切片后的音频总时长{hrs:02d}小时{mins:02d}分{sec}秒{rate_msg}"

input_dir="F:\sliper\input"#输入文件夹(这里面可以放多个wav)
output_dir="F:\sliper\output"#输出文件夹
process_method="丢弃"#如果音频小于3就丢弃
max_sec=15#音频最长为15
min_sec=3#音频最小为3
slicer_fn(input_dir,output_dir,process_method,max_sec,min_sec)

测试输入

得到