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
1d13221a
D
DeepSpeech
项目概览
PaddlePaddle
/
DeepSpeech
大约 1 年 前同步成功
通知
206
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
体验新版 GitCode,发现更多精彩内容 >>
未验证
提交
1d13221a
编写于
2月 07, 2018
作者:
Y
Yang yaming
提交者:
GitHub
2月 07, 2018
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #153 from loongw/develop
make process_utterance accept file object.
上级
422f55a5
a9ccc34a
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
6 addition
and
6 deletion
+6
-6
data_utils/data.py
data_utils/data.py
+6
-6
未找到文件。
data_utils/data.py
浏览文件 @
1d13221a
...
@@ -97,22 +97,22 @@ class DataGenerator(object):
...
@@ -97,22 +97,22 @@ class DataGenerator(object):
self
.
_local_data
.
tar2info
=
{}
self
.
_local_data
.
tar2info
=
{}
self
.
_local_data
.
tar2object
=
{}
self
.
_local_data
.
tar2object
=
{}
def
process_utterance
(
self
,
filenam
e
,
transcript
):
def
process_utterance
(
self
,
audio_fil
e
,
transcript
):
"""Load, augment, featurize and normalize for speech data.
"""Load, augment, featurize and normalize for speech data.
:param
filename: Audio filepath
:param
audio_file: Filepath or file object of audio file.
:type
filenam
e: basestring | file
:type
audio_fil
e: basestring | file
:param transcript: Transcription text.
:param transcript: Transcription text.
:type transcript: basestring
:type transcript: basestring
:return: Tuple of audio feature tensor and data of transcription part,
:return: Tuple of audio feature tensor and data of transcription part,
where transcription part could be token ids or text.
where transcription part could be token ids or text.
:rtype: tuple of (2darray, list)
:rtype: tuple of (2darray, list)
"""
"""
if
filenam
e
.
startswith
(
'tar:'
):
if
isinstance
(
audio_file
,
basestring
)
and
audio_fil
e
.
startswith
(
'tar:'
):
speech_segment
=
SpeechSegment
.
from_file
(
speech_segment
=
SpeechSegment
.
from_file
(
self
.
_subfile_from_tar
(
filenam
e
),
transcript
)
self
.
_subfile_from_tar
(
audio_fil
e
),
transcript
)
else
:
else
:
speech_segment
=
SpeechSegment
.
from_file
(
filenam
e
,
transcript
)
speech_segment
=
SpeechSegment
.
from_file
(
audio_fil
e
,
transcript
)
self
.
_augmentation_pipeline
.
transform_audio
(
speech_segment
)
self
.
_augmentation_pipeline
.
transform_audio
(
speech_segment
)
specgram
,
transcript_part
=
self
.
_speech_featurizer
.
featurize
(
specgram
,
transcript_part
=
self
.
_speech_featurizer
.
featurize
(
speech_segment
,
self
.
_keep_transcription_text
)
speech_segment
,
self
.
_keep_transcription_text
)
...
...
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