Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
PaddlePaddle
DeepSpeech
提交
d0635c65
D
DeepSpeech
项目概览
PaddlePaddle
/
DeepSpeech
大约 2 年 前同步成功
通知
210
Star
8425
Fork
1598
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
245
列表
看板
标记
里程碑
合并请求
3
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
D
DeepSpeech
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
245
Issue
245
列表
看板
标记
里程碑
合并请求
3
合并请求
3
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
未验证
提交
d0635c65
编写于
5月 17, 2021
作者:
H
Hui Zhang
提交者:
GitHub
5月 17, 2021
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
using soxbinddings (#619)
上级
d777edc6
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
33 addition
and
16 deletion
+33
-16
.gitignore
.gitignore
+3
-0
deepspeech/frontend/audio.py
deepspeech/frontend/audio.py
+11
-10
tools/Makefile
tools/Makefile
+19
-6
未找到文件。
.gitignore
浏览文件 @
d0635c65
...
@@ -9,6 +9,9 @@
...
@@ -9,6 +9,9 @@
*.tar.gz
*.tar.gz
.ipynb_checkpoints
.ipynb_checkpoints
*.npz
*.npz
*.done
tools/venv
tools/venv
tools/kenlm
tools/kenlm
tools/sox-14.4.2
tools/soxbindings
deepspeech/frontend/audio.py
浏览文件 @
d0635c65
...
@@ -21,6 +21,7 @@ import struct
...
@@ -21,6 +21,7 @@ import struct
import
numpy
as
np
import
numpy
as
np
import
resampy
import
resampy
import
soundfile
import
soundfile
import
soxbindings
as
sox
from
scipy
import
signal
from
scipy
import
signal
...
@@ -339,18 +340,18 @@ class AudioSegment(object):
...
@@ -339,18 +340,18 @@ class AudioSegment(object):
raise
ValueError
(
"speed_rate should be greater than zero."
)
raise
ValueError
(
"speed_rate should be greater than zero."
)
# numpy
# numpy
old_length
=
self
.
_samples
.
shape
[
0
]
#
old_length = self._samples.shape[0]
new_length
=
int
(
old_length
/
speed_rate
)
#
new_length = int(old_length / speed_rate)
old_indices
=
np
.
arange
(
old_length
)
#
old_indices = np.arange(old_length)
new_indices
=
np
.
linspace
(
start
=
0
,
stop
=
old_length
,
num
=
new_length
)
#
new_indices = np.linspace(start=0, stop=old_length, num=new_length)
self
.
_samples
=
np
.
interp
(
new_indices
,
old_indices
,
self
.
_samples
)
#
self._samples = np.interp(new_indices, old_indices, self._samples)
# sox, slow
# sox, slow
#
tfm = sox.Transformer()
tfm
=
sox
.
Transformer
()
#
tfm.set_globals(multithread=False)
tfm
.
set_globals
(
multithread
=
False
)
#
tfm.speed(speed_rate)
tfm
.
speed
(
speed_rate
)
#
self._samples = tfm.build_array(
self
.
_samples
=
tfm
.
build_array
(
#
input_array=self._samples, sample_rate_in=self._sample_rate).copy()
input_array
=
self
.
_samples
,
sample_rate_in
=
self
.
_sample_rate
).
copy
()
def
normalize
(
self
,
target_db
=-
20
,
max_gain_db
=
300.0
):
def
normalize
(
self
,
target_db
=-
20
,
max_gain_db
=
300.0
):
"""Normalize audio to be of the desired RMS value in decibels.
"""Normalize audio to be of the desired RMS value in decibels.
...
...
tools/Makefile
浏览文件 @
d0635c65
PYTHON
:=
python3.8
PYTHON
:=
python3.8
.PHONY
:
all clean
kenlm
.PHONY
:
all clean
all
:
virtualenv kenlm
all
:
virtualenv kenlm
.done sox.done soxbindings.done
virtualenv
:
virtualenv
:
test
-d
venv
||
virtualenv
-p
$(PYTHON)
venv
test
-d
venv
||
virtualenv
-p
$(PYTHON)
venv
touch
venv/bin/activate
touch
venv/bin/activate
kenlm
:
clean
:
rm
-fr
venv
find
-iname
"*.pyc"
-delete
rm
-rf
kenlm
kenlm.done
:
# Ubuntu 16.04 透過 apt 會安裝 boost 1.58.0
# Ubuntu 16.04 透過 apt 會安裝 boost 1.58.0
# it seems that boost
(
1.54.0
)
requires higher version. After I switched to g++-5 it compiles normally.
# it seems that boost
(
1.54.0
)
requires higher version. After I switched to g++-5 it compiles normally.
apt
install
-y
build-essential cmake libboost-system-dev libboost-thread-dev libboost-program-options-dev libboost-test-dev libeigen3-dev zlib1g-dev libbz2-dev liblzma-dev
apt
install
-y
build-essential cmake libboost-system-dev libboost-thread-dev libboost-program-options-dev libboost-test-dev libeigen3-dev zlib1g-dev libbz2-dev liblzma-dev
...
@@ -15,8 +20,16 @@ kenlm:
...
@@ -15,8 +20,16 @@ kenlm:
test
-d
kenlm
||
wget
-O
- https://kheafield.com/code/kenlm.tar.gz |
tar
xz
test
-d
kenlm
||
wget
-O
- https://kheafield.com/code/kenlm.tar.gz |
tar
xz
mkdir
-p
kenlm/build
&&
cd
kenlm/build
&&
cmake ..
&&
make
-j4
&&
make
install
mkdir
-p
kenlm/build
&&
cd
kenlm/build
&&
cmake ..
&&
make
-j4
&&
make
install
cd
kenlm
&&
python setup.py
install
cd
kenlm
&&
python setup.py
install
touch
kenlm.done
clean
:
sox.done
:
rm
-fr
venv
apt
install
-y
libvorbis-dev libmp3lame-dev libmad-ocaml-dev
find
-iname
"*.pyc"
-delete
test
-d
sox-14.4.2
||
wget https://nchc.dl.sourceforge.net/project/sox/sox/14.4.2/sox-14.4.2.tar.gz
tar
-xvzf
sox-14.4.2.tar.gz
-C
.
cd
sox-14.4.2
&&
./configure
--prefix
=
/usr/
&&
make
-j4
&&
make
install
touch
sox.done
soxbindings.done
:
test
-d
soxbindings
||
git clone https://github.com/pseeth/soxbindings.git
source
venv/bin/activate
;
cd
soxbindings
&&
python3 setup.py
install
touch
soxbindings.done
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录