基于PaddleSpeech搭建个人语音听写服务

.需求分析

亲们，你们要写会议纪要嘛？
亲们，你们要写会议纪要嘛？
亲们，你们要写会议纪要嘛？

当您面对成吨的会议录音，着急写会议纪要而不得不愚公移山、人海战术？听的头晕眼花，听的漏洞百出，听的怀疑人生，那么你是否想到了自动听写服务？
想想也是，百度一看，好家伙，收费不菲啊！请看下图

2.需求再分析
亲密，能花钱解决的都不是事，刚刚看到听写服务，很贵的，大致1400大洋，还是打折完毕的，而且还是云服务形式的，那么对于某些会议，比如保密会议，需要离线的，那么完全办不到，该怎么办呢？
下面就有请我们的PaddleSpeech出场来解决问题。
3.解决思路
【超简单】之基于PaddleSpeech搭建个人语音听写服务，顾名思义，是通过PaddleSpeech来搭建语音听写服务的，主要思路如下。

1.录音长度切分
2.录音听写
3.录音文本加标点

二、环境搭建
1.PaddleSpeech简介
PaddleSpeech 是基于飞桨 PaddlePaddle 的语音方向的开源模型库，用于语音和音频中的各种关键任务的开发，包含大量基于深度学习前沿和有影响力的模型，一些典型的应用如下：

语音识别
语音翻译
语音合成

2.PaddleSpeech安装
pip install paddlespeech
复制代码
2.1相关依赖

gcc >= 4.8.5
paddlepaddle >= 2.3.1
python >= 3.7
linux(推荐), mac, windows

2.2 win安装注意事项

1.win必须安装 Microsoft C++ 生成工具 - Visual Studio
visualstudio.microsoft.com/zh-hans/vis… 工具，原因是安装非纯 Python 包或编译 Cython 或 Pyrex 文件。

2.参考： WindowsCompilers - Python Wiki
wiki.python.org/moin/Window…

!pip install paddlespeech >log.log
复制代码
2.3 快速试用
!wget -c https://paddlespeech.bj.bcebo...
复制代码
--2022-07-27 00:31:57-- https://paddlespeech.bj.bcebo...
Resolving paddlespeech.bj.bcebos.com (paddlespeech.bj.bcebos.com)... 182.61.200.195, 182.61.200.229, 2409:8c04:1001:1002:0:ff:b001:368a
Connecting to paddlespeech.bj.bcebos.com (paddlespeech.bj.bcebos.com)|182.61.200.195|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 159942 (156K) [audio/wav]
Saving to: ‘zh.wav’

zh.wav 100%[===================>] 156.19K --.-KB/s in 0.03s

2022-07-27 00:31:57 (5.52 MB/s) - ‘zh.wav’ saved [159942/159942]
复制代码
2.3.1 API调用
from paddlespeech.cli.asr.infer import ASRExecutor

asr = ASRExecutor()
result = asr(audio_file="zh.wav")
复制代码
[2022-07-27 00:33:02,175] [ INFO] - checking the audio file format......
复制代码
print(result)
复制代码
我认为跑步最重要的就是给我带来了身体健康
复制代码
2.3.2 命令行调用
!paddlespeech asr --lang zh --input zh.wav
复制代码
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/nltk/decorators.py:68: DeprecationWarning: formatargspec is deprecated since Python 3.5. Use signature and the Signature object directly
regargs, varargs, varkwargs, defaults, formatvalue=lambda value: ""
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/nltk/lm/counter.py:15: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
from collections import Sequence, defaultdict
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/nltk/lm/vocabulary.py:13: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
from collections import Counter, Iterable
[nltk_data] Downloading package averaged_perceptron_tagger to
[nltk_data] /home/aistudio/nltk_data...
[nltk_data] Unzipping taggers/averaged_perceptron_tagger.zip.
[nltk_data] Downloading package cmudict to /home/aistudio/nltk_data...
[nltk_data] Unzipping corpora/cmudict.zip.
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/__init__.py:107: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
from collections import MutableMapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/rcsetup.py:20: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
from collections import Iterable, Mapping
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/matplotlib/colors.py:53: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated, and in 3.8 it will stop working
from collections import Sized
W0727 00:38:55.935500 2181 gpu_resources.cc:61] Please NOTE: device: 0, GPU Compute Capability: 7.0, Driver API Version: 11.2, Runtime API Version: 10.1
W0727 00:38:55.940197 2181 gpu_resources.cc:91] device: 0, cuDNN Version: 7.6.
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/h5py/__init__.py:36: DeprecationWarning: np.typeDict is a deprecated alias for np.sctypeDict.
from ._conv import register_converters as _register_converters
我认为跑步最重要的就是给我带来了身体健康
复制代码
会自动下载一堆东西有点慢，可以不用这个。
[nltk_data] Downloading package averaged_perceptron_tagger to
[nltk_data] /home/aistudio/nltk_data...
[nltk_data] Unzipping taggers/averaged_perceptron_tagger.zip.
[nltk_data] Downloading package cmudict to /home/aistudio/nltk_data...
复制代码
2.3.3 常见错误
如遇到以下错误
[2022-07-26 21:13:28,589] [ INFO] - checking the audio file format......
[2022-07-26 21:13:28,594] [ ERROR] - Please input audio file less then 50 seconds.
复制代码
报错很明显，提示一个是音频格式问题，一个是小于50s问题，如果遇到这个问题后面解决。

1.音频必须为wav格式

2.音频大小必须小于50s

音频格式为wav格式，这个可通过录音笔设置（一般默认），或python代码转换，或者格式工厂进行转换。
3.音频切分
此处使用auditok库
!pip install auditok
复制代码
Looking in indexes: https://pypi.tuna.tsinghua.ed...
Collecting auditok
Downloading https://pypi.tuna.tsinghua.ed... (1.5 MB)

 l     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.0/1.5 MB ? eta -:--:--━━━━━━━━━━╸━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 0.4/1.5 MB 14.2 MB/s eta 0:00:01━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╸━━━━━━ 1.3/1.5 MB 19.7 MB/s eta 0:00:01━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.5/1.5 MB 15.4 MB/s eta 0:00:00

[?25hInstalling collected packages: auditok
Successfully installed auditok-0.2.0

[notice] A new release of pip available: 22.1.2 -> 22.2
[notice] To update, run: pip install --upgrade pip
复制代码
三、音频切分
切分原因上面交代过，因为PaddleSpeech识别最长语音为50s，故需要切分，这里直接调用好了。
from paddlespeech.cli.asr.infer import ASRExecutor
import csv
import moviepy.editor as mp
import auditok
import os
import paddle
from paddlespeech.cli import ASRExecutor, TextExecutor
import soundfile
import librosa
import warnings

warnings.filterwarnings('ignore')
复制代码

引入auditok库

import auditok

输入类别为audio

def qiefen(path, ty='audio', mmin_dur=1, mmax_dur=100000, mmax_silence=1, menergy_threshold=55):

audio_file = path
audio, audio_sample_rate = soundfile.read(
    audio_file, dtype="int16", always_2d=True)

audio_regions = auditok.split(
    audio_file,
    min_dur=mmin_dur,  # minimum duration of a valid audio event in seconds
    max_dur=mmax_dur,  # maximum duration of an event
    # maximum duration of tolerated continuous silence within an event
    max_silence=mmax_silence,
    energy_threshold=menergy_threshold  # threshold of detection
)

for i, r in enumerate(audio_regions):
    # Regions returned by `split` have 'start' and 'end' metadata fields
    print(
        "Region {i}: {r.meta.start:.3f}s -- {r.meta.end:.3f}s".format(i=i, r=r))

    epath = ''
    file_pre = str(epath.join(audio_file.split('.')[0].split('/')[-1]))

    mk = 'change'
    if (os.path.exists(mk) == False):
        os.mkdir(mk)
    if (os.path.exists(mk + '/' + ty) == False):
        os.mkdir(mk + '/' + ty)
    if (os.path.exists(mk + '/' + ty + '/' + file_pre) == False):
        os.mkdir(mk + '/' + ty + '/' + file_pre)
    num = i
    # 为了取前三位数字排序
    s = '000000' + str(num)

    file_save = mk + '/' + ty + '/' + file_pre + '/' + \
                s[-3:] + '-' + '{meta.start:.3f}-{meta.end:.3f}' + '.wav'
    filename = r.save(file_save)
    print("region saved as: {}".format(filename))
return mk + '/' + ty + '/' + file_pre

引入auditok库

输入类别为audio

android内涵段子项目-(架构第一期)

Android进阶之旅-(Framework源码分析)

热门文章