preparing recipe timit

src/SpeechCorpora.jl

@@ -23,11 +23,15 @@ export
 
     # Corpora interface
     download,
+    lang,
+    name,
+    path,
     prepare,
 
     # Corpora
     MultilingualLibriSpeech,
-    MiniLibriSpeech
+    MiniLibriSpeech,
+    TIMIT
 
 
 
@@ -46,5 +50,6 @@ include("manifest_item.jl")
 include("manifest_io.jl")
 include("corpora/multilingual_librispeech.jl")
 include("corpora/mini_librispeech.jl")
+include("corpora/timit.jl")
 
 end

src/corpora/timit.jl

+# SPDX-License-Identifier: CECILL-2.1
+
+#######################################################################
+
+const TIMIT_SUBSETS = Dict(
+    "train" => "train",
+    "dev" => "dev",
+    "test" => "test"
+)
+
+const TIMIT_LANG = "eng"
+const TIMIT_NAME = "timit"
+
+const TIMIT_DEV_SPK_LIST = Set([
+    "faks0",
+    "fdac1",
+    "fjem0",
+    "mgwt0",
+    "mjar0",
+    "mmdb1",
+    "mmdm2",
+    "mpdf0",
+    "fcmh0",
+    "fkms0",
+    "mbdg0",
+    "mbwm0",
+    "mcsh0",
+    "fadg0",
+    "fdms0",
+    "fedw0",
+    "mgjf0",
+    "mglb0",
+    "mrtk0",
+    "mtaa0",
+    "mtdt0",
+    "mthc0",
+    "mwjg0",
+    "fnmr0",
+    "frew0",
+    "fsem0",
+    "mbns0",
+    "mmjr0",
+    "mdls0",
+    "mdlf0",
+    "mdvc0",
+    "mers0",
+    "fmah0",
+    "fdrw0",
+    "mrcs0",
+    "mrjm4",
+    "fcal1",
+    "mmwh0",
+    "fjsj0",
+    "majc0",
+    "mjsw0",
+    "mreb0",
+    "fgjd0",
+    "fjmg0",
+    "mroa0",
+    "mteb0",
+    "mjfc0",
+    "mrjr0",
+    "fmml0",
+    "mrws1"
+])
+
+const TIMIT_TEST_SPK_LIST = Set([
+    "mdab0",
+    "mwbt0",
+    "felc0",
+    "mtas1",
+    "mwew0",
+    "fpas0",
+    "mjmp0",
+    "mlnt0",
+    "fpkt0",
+    "mlll0",
+    "mtls0",
+    "fjlm0",
+    "mbpm0",
+    "mklt0",
+    "fnlp0",
+    "mcmj0",
+    "mjdh0",
+    "fmgd0",
+    "mgrt0",
+    "mnjm0",
+    "fdhc0",
+    "mjln0",
+    "mpam0",
+    "fmld0"
+])
+
+TIMIT_PHONE_MAP48 = Dict(
+    "aa"    => "aa",
+    "ae"    => "ae",
+    "ah"    => "ah",
+    "ao"    => "ao",
+    "aw"    => "aw",
+    "ax"    => "ax",
+    "ax-h"  => "ax",
+    "axr"   => "er",
+    "ay"    => "ay",
+    "b"     => "b",
+    "bcl"   => "vcl",
+    "ch"    => "ch",
+    "d"     => "d",
+    "dcl"   => "vcl",
+    "dh"    => "dh",
+    "dx"    => "dx",
+    "eh"    => "eh",
+    "el"    => "el",
+    "em"    => "m",
+    "en"    => "en",
+    "eng"   => "ng",
+    "epi"   => "epi",
+    "er"    => "er",
+    "ey"    => "ey",
+    "f"     => "f",
+    "g"     => "g",
+    "gcl"   => "vcl",
+    "h#"    => "sil",
+    "hh"    => "hh",
+    "hv"    => "hh",
+    "ih"    => "ih",
+    "ix"    => "ix",
+    "iy"    => "iy",
+    "jh"    => "jh",
+    "k"     => "k",
+    "kcl"   => "cl",
+    "l"     => "l",
+    "m"     => "m",
+    "n"     => "n",
+    "ng"    => "ng",
+    "nx"    => "n",
+    "ow"    => "ow",
+    "oy"    => "oy",
+    "p"     => "p",
+    "pau"   => "sil",
+    "pcl"   => "cl",
+    "q"     => "",
+    "r"     => "r",
+    "s"     => "s",
+    "sh"    => "sh",
+    "t"     => "t",
+    "tcl"   => "cl",
+    "th"    => "th",
+    "uh"    => "uh",
+    "uw"    => "uw",
+    "ux"    => "uw",
+    "v"     => "v",
+    "w"     => "w",
+    "y"     => "y",
+    "z"     => "z",
+    "zh"    => "zh"
+)
+
+#######################################################################
+
+struct TIMIT<: SpeechCorpus
+    datapath::AbstractString
+end
+
+lang(::TIMIT) = "eng"
+name(::TIMIT) = "timit"
+
+function prepare(timit::TIMIT)
+
+end
+

src/speechcorpus.jl

@@ -7,24 +7,38 @@ Abstract type for all speech corpora.
 """
 abstract type SpeechCorpus end
 
+"""
+    lang(corpus)
+
+Return the ISO 639-3 code of the language of the corpus.
+"""
+lang
+
+"""
+    name(corpus)
+
+Return the name identifier of the corpus.
+"""
+name
+
 """
     path(corpus)
 
-Path to the directory where is stored the corpus' data.
+Path to the directory where are stored the manifests of the corpus.
 """
-path(corpus::SpeechCorpus, dir) = joinpath(dir, corpus.lang, corpus.name)
+path(corpus::SpeechCorpus) = joinpath(dir, corpus.lang, corpus.name)
 
 """
-    download(corpus[, dir = homedir()])
+    download(corpus)
 
 Download the data of the corpus to `dir`.
 """
-Base.download(corpus::SpeechCorpus) = download(corpus, SPEECH_CORPORA_ROOTDIR)
+Base.download(corpus::SpeechCorpus)
 
 """
-    prepare(corpus[, dir = homedir()])
+    prepare(corpus)
 
-Prepare the manifests of corpus to `dir`.
+Prepare the manifests of corpus.
 """
-prepare(corpus::SpeechCorpus) = prepare(corpus, SPEECH_CORPORA_ROOTDIR)
+prepare(corpus::SpeechCorpus)