@@ -101,7 +101,6 @@ they have | they've
101101you've | you have
102102you have | you've
103103
104- # TODO: which other contractions?
105104
106105'cause | cause ; because
107106because | 'cause ; cause
@@ -125,41 +124,27 @@ outta | out of
125124what are you | whatcha
126125whatcha | what are you
127126
128- # handling comments/annotations in the nlp files
129- # note: anything after a : is ignored for now
130- # how to mimig deletions... ε or <del>?
131- # both options cause problems right now, so we'll avoid that for now
132- <barking> | <del> ; <unk>
133- <cheer> | <del> ; <unk>
134- <clap> | <del> ; <unk>
135- <clear_throat> | <del> ; <unk>
136- <cough> | <del> ; <unk>
137- <crosstalk> | <del> ; <unk>
138- <cry> | <del> ; <unk>
139- <finger_snap> | <del> ; <unk>
140- <foreign> | <del> ; <unk>
141- # <foreign:{note}> | <del> ; <unk>
142- <groan> | <del> ; <unk>
143- <grunt> | <del> ; <unk>
144- <inaudible> | <del> ; <unk>
145- <laugh> | <del> ; <unk>
146- # <laugh:chuckle> | <del> ; <unk>
147- # <laugh:{note}> | <del> ; <unk>
148- <mumble> | <del> ; <unk>
149- <murmur> | <del> ; <unk>
150- <phonetic> | <del> ; <unk>
151- <scream> | <del> ; <unk>
152- <sigh> | <del> ; <unk>
153- <silence> | <del> ; <unk>
154- # <silence:blank_audio> | <del> ; <unk>
155- # <silence:pause> | <del> ; <unk>
156- # <silence:pause> | <del> ; <unk>
157- <sing> | <del> ; <unk>
158- <siren> | <del> ; <unk>
159- <unk> | <del> ; <unk>
160- <visual> | <del> ; <unk>
161- # <visual:{note}> | <del> ; <unk>
162- <yawn> | <del> ; <unk>
163-
164- # anything not explicitly handled will be ignored from the graph
165- #<{note}> | <del>
127+ <barking> | <unk>
128+ <cheer> | <unk>
129+ <clap> | <unk>
130+ <clear_throat> | <unk>
131+ <cough> | <unk>
132+ <crosstalk> | <unk>
133+ <cry> | <unk>
134+ <finger_snap> | <unk>
135+ <foreign> | <unk>
136+ <groan> | <unk>
137+ <grunt> | <unk>
138+ <inaudible> | <unk>
139+ <laugh> | <unk>
140+ <mumble> | <unk>
141+ <murmur> | <unk>
142+ <phonetic> | <unk>
143+ <scream> | <unk>
144+ <sigh> | <unk>
145+ <silence> | <unk>
146+ <sing> | <unk>
147+ <siren> | <unk>
148+ <unk> | <unk>
149+ <visual> | <unk>
150+ <yawn> | <unk>
0 commit comments