remove comments and replace original paths to corpora with generic paths

bpe-gl-en_emb.yaml

@@ -8,63 +8,48 @@ overwrite: True
 # Corpus opts:
 data:
     europarl:
-        path_src: ../DGTcorpora_tokenized/en_gl/europarl/partitions/en_train.txt
-        path_tgt: ../DGTcorpora_tokenized/en_gl/europarl/partitions/gl_train.txt
+        path_src: corpora/europarl/partitions/en_train.txt
+        path_tgt: corpora/europarl/partitions/gl_train.txt
         transforms: [bpe, filtertoolong]
         weight: 120
     opensub:
-        path_tgt: ../DGTcorpora_tokenized/en_gl/opensub/partitions/en_train.txt
-        path_src: ../DGTcorpora_tokenized/en_gl/opensub/partitions/gl_train.txt
+        path_tgt: corpora/opensub/partitions/en_train.txt
+        path_src: corpora/opensub/partitions/gl_train.txt
         transforms: [bpe, filtertoolong]
         weight: 152
     opus:
-        path_tgt: ../DGTcorpora_tokenized/en_gl/opus/partitions/en_train.txt
-        path_src: ../DGTcorpora_tokenized/en_gl/opus/partitions/gl_train.txt
+        path_tgt: corpora/opus/partitions/en_train.txt
+        path_src: corpora/opus/partitions/gl_train.txt
         transforms: [bpe, filtertoolong]
         weight: 160
     ted2020:
-        path_tgt: ../DGTcorpora_tokenized/en_gl/ted2020/partitions/en_train.txt
-        path_src: ../DGTcorpora_tokenized/en_gl/ted2020/partitions/gl_train.txt
+        path_tgt: corpora/ted2020/partitions/en_train.txt
+        path_src: corpora/ted2020/partitions/gl_train.txt
         transforms: [bpe, filtertoolong]
         weight: 10
     corgaback:
-        path_tgt: ../DGTcorpora_tokenized/en_gl/corgaback/partitions/en_train.txt
-        path_src: ../DGTcorpora_tokenized/en_gl/corgaback/partitions/gl_train.txt
+        path_tgt: corpora/corgaback/partitions/en_train.txt
+        path_src: corpora/corgaback/partitions/gl_train.txt
         transforms: [bpe, filtertoolong]
         weight: 15
     ccmatrix:
-        path_tgt: ../DGTcorpora_tokenized/en_gl/ccmatrix/en_tok_dbo.txt
-        path_src: ../DGTcorpora_tokenized/en_gl/ccmatrix/gl_tok_dbo.txt
+        path_tgt: corpora/ccmatrix/en_tok_dbo.txt
+        path_src: corpora/ccmatrix/gl_tok_dbo.txt
         transforms: [bpe, filtertoolong]
-        weight: 380 ##75 ## 25000000/13000000 = 2; 760/2 = 380 * 5 = 1900 (380/5=75)
+        weight: 380
     wikimatrix:
-        path_tgt: ../DGTcorpora_tokenized/en_gl/wikimatrix/en.txt
-        path_src: ../DGTcorpora_tokenized/en_gl/wikimatrix/gl.txt
+        path_tgt: corpora/wikimatrix/en.txt
+        path_src: corpora/wikimatrix/gl.txt
         transforms: [bpe, filtertoolong]
-        weight: 70 #25000000/450000 = 55 ; 760/55 = 14 ; 14 * 5 = 70
+        weight: 70 
     cluvi:
-        path_tgt: ../DGTcorpora_tokenized/en_gl/cluvi/en.txt
-        path_src: ../DGTcorpora_tokenized/en_gl/cluvi/gl.txt
+        path_tgt: corpora/cluvi/en.txt
+        path_src: corpora/cluvi/gl.txt
         transforms: [bpe, filtertoolong]
-        weight: 70 #25000000/295000 = 84 ; 760/84 = 9 ; 9 * 10 = 90
-        #wikimedia:
-        # path_tgt: ../DGTcorpora_tokenized/en_gl/wikimedia/en.txt
-        #path_src: ../DGTcorpora_tokenized/en_gl/wikimedia/gl.txt
-        #transforms: [bpe, filtertoolong]
-        #weight: 4
-        # xlent:
-        #path_tgt: ../DGTcorpora_tokenized/en_gl/xlent/en.txt
-        #path_src: ../DGTcorpora_tokenized/en_gl/xlent/gl.txt
-        #transforms: [bpe, filtertoolong]
-        #weight: 50 #25000000/1600000=15; 760/15=50
-        #linux:
-        #path_tgt: ../DGTcorpora_tokenized/en_gl/linux/en.txt
-        #path_src: ../DGTcorpora_tokenized/en_gl/linux/gl.txt
-        #transforms: [bpe, filtertoolong]
-        #weight: 20 #25000000/150000=166; 760/166=5 * 5 = 20
+        weight: 70
     valid:
-        path_tgt: ../DGTcorpora_tokenized/en_gl/partitions/all-en_valid.txt
-        path_src: ../DGTcorpora_tokenized/en_gl/partitions/all-gl_valid.txt
+        path_tgt: corpora/partitions/all-en_valid.txt
+        path_src: corpora/partitions/all-gl_valid.txt
         transforms: [bpe, filtertoolong]
 
 ### Transform related opts:
@@ -73,8 +58,6 @@ tgt_subword_model: ./bpe/en.code
 src_subword_model: ./bpe/gl.code
 src_subword_vocab: ./run/bpe.vocab.src
 tgt_subword_vocab: ./run/bpe.vocab.tgt
-#tgt_subword_model: ../sentencepiece/en-gl/en.sp.model
-#src_subword_model: ../sentencepiece/en-gl/gl.sp.model
 src_subword_type: bpe
 tgt_subord_type: bpe