Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
S
SpeechDatasets.jl
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package Registry
Container Registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
PTAL
Datasets
SpeechDatasets.jl
Commits
3f0ec788
Verified
Commit
3f0ec788
authored
2 years ago
by
Lucas Ondel Yang
Browse files
Options
Downloads
Patches
Plain Diff
updated readme and changelog
parent
386df4df
No related branches found
No related tags found
No related merge requests found
Changes
4
Hide whitespace changes
Inline
Side-by-side
Showing
4 changed files
Project.toml
+1
-1
1 addition, 1 deletion
Project.toml
README.md
+1
-1
1 addition, 1 deletion
README.md
src/SpeechCorpora.jl
+3
-1
3 additions, 1 deletion
src/SpeechCorpora.jl
src/corpora/multilingual_librispeech.jl
+5
-5
5 additions, 5 deletions
src/corpora/multilingual_librispeech.jl
with
10 additions
and
8 deletions
Project.toml
+
1
−
1
View file @
3f0ec788
name
=
"SpeechCorpora"
name
=
"SpeechCorpora"
uuid
=
"3225a15e-d855-4a07-9546-2418058331ae"
uuid
=
"3225a15e-d855-4a07-9546-2418058331ae"
authors
=
[
"Lucas ONDEL YANG <lucas.ondel@cnrs.fr>"
]
authors
=
[
"Lucas ONDEL YANG <lucas.ondel@cnrs.fr>"
]
version
=
"0.
1.1
"
version
=
"0.
2.0
"
[deps]
[deps]
HTTP
=
"cd3eb016-35fb-5094-929b-558a96fad6f3"
HTTP
=
"cd3eb016-35fb-5094-929b-558a96fad6f3"
...
...
This diff is collapsed.
Click to expand it.
README.md
+
1
−
1
View file @
3f0ec788
...
@@ -4,7 +4,7 @@ A Julia package to download and prepare speech corpus.
...
@@ -4,7 +4,7 @@ A Julia package to download and prepare speech corpus.
## Installation
## Installation
Make sure to add the
[
FAST registry
](
https://
src.koda.cnrs
.fr/fast/registry
)
Make sure to add the
[
FAST registry
](
https://
gitlab.lisn.upsaclay
.fr/fast/registry
)
to your julia installation. Then, install the package as usual:
to your julia installation. Then, install the package as usual:
```
```
pkg> add SpeechCorpora
pkg> add SpeechCorpora
...
...
This diff is collapsed.
Click to expand it.
src/SpeechCorpora.jl
+
3
−
1
View file @
3f0ec788
...
@@ -23,11 +23,13 @@ export
...
@@ -23,11 +23,13 @@ export
prepare
,
prepare
,
# Corpora
# Corpora
MultilingualLibriSpeech
MultilingualLibriSpeech
,
MiniLibriSpeech
include
(
"manifest_item.jl"
)
include
(
"manifest_item.jl"
)
include
(
"manifest_io.jl"
)
include
(
"manifest_io.jl"
)
include
(
"corpora/multilingual_librispeech.jl"
)
include
(
"corpora/multilingual_librispeech.jl"
)
include
(
"corpora/mini_librispeech.jl"
)
end
end
This diff is collapsed.
Click to expand it.
src/corpora/multilingual_librispeech.jl
+
5
−
5
View file @
3f0ec788
...
@@ -59,7 +59,7 @@ function Base.download(::MultilingualLibriSpeechCorpus, lang, outdir)
...
@@ -59,7 +59,7 @@ function Base.download(::MultilingualLibriSpeechCorpus, lang, outdir)
@info
"dataset in
$
outdir"
@info
"dataset in
$
outdir"
end
end
function
recordings
(
lang
,
dir
,
subset
)
function
recordings
(
::
MultilingualLibriSpeechCorpus
,
lang
,
dir
,
subset
)
subsetdir
=
joinpath
(
dir
,
"mls_
$
(MLS_LANG_CODE[lang])"
,
subset
,
"audio"
)
subsetdir
=
joinpath
(
dir
,
"mls_
$
(MLS_LANG_CODE[lang])"
,
subset
,
"audio"
)
recs
=
Dict
()
recs
=
Dict
()
...
@@ -80,7 +80,7 @@ function recordings(lang, dir, subset)
...
@@ -80,7 +80,7 @@ function recordings(lang, dir, subset)
recs
recs
end
end
function
supervisions
(
lang
,
dir
,
subset
)
function
supervisions
(
::
MultilingualLibriSpeechCorpus
,
lang
,
dir
,
subset
)
trans
=
joinpath
(
dir
,
"mls_
$
(MLS_LANG_CODE[lang])"
,
subset
,
"transcripts.txt"
)
trans
=
joinpath
(
dir
,
"mls_
$
(MLS_LANG_CODE[lang])"
,
subset
,
"transcripts.txt"
)
sups
=
Dict
()
sups
=
Dict
()
open
(
trans
,
"r"
)
do
f
open
(
trans
,
"r"
)
do
f
...
@@ -94,13 +94,13 @@ function supervisions(lang, dir, subset)
...
@@ -94,13 +94,13 @@ function supervisions(lang, dir, subset)
sups
sups
end
end
function
prepare
(
::
MultilingualLibriSpeechCorpus
,
lang
,
dir
)
function
prepare
(
multils
::
MultilingualLibriSpeechCorpus
,
lang
,
dir
)
# 1. Recording manifests.
# 1. Recording manifests.
for
subset
in
[
"train"
,
"dev"
,
"test"
]
for
subset
in
[
"train"
,
"dev"
,
"test"
]
out
=
joinpath
(
dir
,
"recording-manifest-
$
subset.jsonl"
)
out
=
joinpath
(
dir
,
"recording-manifest-
$
subset.jsonl"
)
@info
"preparing recording manifest (
$
subset)
$
out"
@info
"preparing recording manifest (
$
subset)
$
out"
if
!
isfile
(
out
)
if
!
isfile
(
out
)
recs
=
recordings
(
lang
,
dir
,
subset
)
recs
=
recordings
(
multils
,
lang
,
dir
,
subset
)
open
(
out
,
"w"
)
do
f
open
(
out
,
"w"
)
do
f
writemanifest
(
f
,
recs
)
writemanifest
(
f
,
recs
)
end
end
...
@@ -112,7 +112,7 @@ function prepare(::MultilingualLibriSpeechCorpus, lang, dir)
...
@@ -112,7 +112,7 @@ function prepare(::MultilingualLibriSpeechCorpus, lang, dir)
out
=
joinpath
(
dir
,
"supervision-manifest-
$
subset.jsonl"
)
out
=
joinpath
(
dir
,
"supervision-manifest-
$
subset.jsonl"
)
@info
"preparing supervision manifest (
$
subset)
$
out"
@info
"preparing supervision manifest (
$
subset)
$
out"
if
!
isfile
(
out
)
if
!
isfile
(
out
)
sups
=
supervisions
(
lang
,
dir
,
subset
)
sups
=
supervisions
(
multils
,
lang
,
dir
,
subset
)
open
(
out
,
"w"
)
do
f
open
(
out
,
"w"
)
do
f
writemanifest
(
f
,
sups
)
writemanifest
(
f
,
sups
)
end
end
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment