Merge branch 'test' into 'main'

rename Supervision calls to Annotation

See merge request fast/speechdatasets.jl!14

src/corpora/mini_librispeech.jl

@@ -42,7 +42,7 @@ function minils_recordings(dir, subset)
     recs
 end
 
-function minils_supervisions(dir, subset)
+function minils_annotations(dir, subset)
     subsetdir = joinpath(dir, "LibriSpeech", MINILS_SUBSETS[subset])
     sups = Dict()
     for d1 in readdir(subsetdir; join = true)
@@ -52,8 +52,8 @@ function minils_supervisions(dir, subset)
             open(joinpath(d2, "$(k1)-$(k2).trans.txt"), "r") do f
                 for line in eachline(f)
                     tokens = split(line)
-                    s = Supervision(
-                        tokens[1], # supervision id
+                    s = Annotation(
+                        tokens[1], # annotation id
                         tokens[1]; # recording id
                         channels = [1],
                         data = Dict("text" => join(tokens[2:end], " "))
@@ -98,12 +98,12 @@ function minils_prepare(dir)
         end
     end
 
-    # 2. Supervision manifests.
+    # 2. Annotation manifests.
     for (subset, name) in [("train", "train"), ("dev", "dev"), ("dev", "test")]
-        out = joinpath(dir, "supervisions-$name.jsonl")
+        out = joinpath(dir, "annotations-$name.jsonl")
         if ! isfile(out)
-            @debug "preparing supervision manifest ($subset) $out"
-            sups = minils_supervisions(dir, subset)
+            @debug "preparing annotation manifest ($subset) $out"
+            sups = minils_annotations(dir, subset)
             open(out, "w") do f
                 writemanifest(f, sups)
             end

src/corpora/multilingual_librispeech.jl

@@ -89,13 +89,13 @@ function recordings(corpus::MultilingualLibriSpeech, dir, subset)
     recs
 end
 
-function supervisions(corpus::MultilingualLibriSpeech, dir, subset)
+function annotations(corpus::MultilingualLibriSpeech, dir, subset)
     trans = joinpath(dir, "mls_$(MLS_LANG_CODE[corpus.lang])", subset, "transcripts.txt")
     sups = Dict()
     open(trans, "r") do f
         for line in eachline(f)
             tokens = split(line)
-            s = Supervision(tokens[1], tokens[1]; channel = 1,
+            s = Annotation(tokens[1], tokens[1]; channel = 1,
                             data = Dict("text" => join(tokens[2:end], " ")))
             sups[s.id] = s
         end
@@ -118,12 +118,12 @@ function prepare(corpus::MultilingualLibriSpeech, outdir)
         end
     end
 
-    # 2. Supervision manifests.
+    # 2. Annotation manifests.
     for subset in ["train", "dev", "test"]
-        out = joinpath(dir, "supervision-manifest-$subset.jsonl")
-        @info "preparing supervision manifest ($subset) $out"
+        out = joinpath(dir, "annotation-manifest-$subset.jsonl")
+        @info "preparing annotation manifest ($subset) $out"
         if ! isfile(out)
-            sups = supervisions(corpus, dir, subset)
+            sups = annotations(corpus, dir, subset)
             open(out, "w") do f
                 writemanifest(f, sups)
             end