build read_audio function and add audio.json

data/testcorpus/conversations.json

@@ -0,0 +1 @@
+{"/ulwa1/ulwa014": {"meta": {}, "vectors": []}}

data/testcorpus/corpus.json

@@ -0,0 +1 @@
+{}

data/testcorpus/index.json

@@ -0,0 +1 @@
+{"utterances-index": {}, "speakers-index": {}, "conversations-index": {}, "overall-index": {}, "version": 1, "vectors": []}

data/testcorpus/speakers.json

@@ -0,0 +1 @@
+{"Tang": {"meta": {}, "vectors": []}, "Yan": {"meta": {}, "vectors": []}}

data/testcorpus/utterances.jsonl

@@ -0,0 +1,10 @@
+{"id": "0", "conversation_id": "/ulwa1/ulwa014", "text": "U oughs inim t\u00ef samting yan", "speaker": "Tang", "meta": {}, "reply-to": null, "timestamp": 1332718704, "vectors": []}
+{"id": "1", "conversation_id": "/ulwa1/ulwa014", "text": "mbam ndul ma wandam ana", "speaker": "Yan", "meta": {}, "reply-to": null, "timestamp": 1332732704, "vectors": []}
+{"id": "2", "conversation_id": "/ulwa1/ulwa014", "text": "M\u00ef inim wandam bai anapa nd", "speaker": "Tang", "meta": {}, "reply-to": null, "timestamp": 1332743704, "vectors": []}
+{"id": "3", "conversation_id": "/ulwa1/ulwa014", "text": "lunda we nd\u00efm\u00efne in", "speaker": "Yan", "meta": {}, "reply-to": null, "timestamp": 1332754704, "vectors": []}
+{"id": "4", "conversation_id": "/ulwa1/ulwa014", "text": "k\u00efnakape ak\u00efnaka", "speaker": "Tang", "meta": {}, "reply-to": null, "timestamp": 1332765704, "vectors": []}
+{"id": "5", "conversation_id": "/ulwa1/ulwa014", "text": "coughs nd\u00efm\u00efne we ndul wa le we nd\u00eft\u00ef ak\u00efnakape malimap mat\u00ef yawa mananda", "speaker": "Yan", "meta": {}, "reply-to": null, "timestamp": 1332776704, "vectors": []}
+{"id": "6", "conversation_id": "/ulwa1/ulwa014", "text": "mananda", "speaker": "Tang", "meta": {}, "reply-to": null, "timestamp": 1332787704, "vectors": []}
+{"id": "7", "conversation_id": "/ulwa1/ulwa014", "text": "da", "speaker": "Yan", "meta": {}, "reply-to": null, "timestamp": 1332788704, "vectors": []}
+{"id": "8", "conversation_id": "/ulwa1/ulwa014", "text": "e k\u00efkal awi ak\u00efnakape", "speaker": "Tang", "meta": {}, "reply-to": null, "timestamp": 1332789704, "vectors": []}
+{"id": "9", "conversation_id": "/ulwa1/ulwa014", "text": "at\u00efm inim.", "speaker": "Yan", "meta": {}, "reply-to": null, "timestamp": 1332999704, "vectors": []}

data/ulwa json corpus/conversations.json

@@ -0,0 +1 @@
+{"/ulwa1/ulwa014": {"meta": {}, "vectors": []}}

data/ulwa json corpus/corpus.json

@@ -0,0 +1 @@
+{}

data/ulwa json corpus/index.json

@@ -0,0 +1 @@
+{"utterances-index": {}, "speakers-index": {}, "conversations-index": {}, "overall-index": {}, "version": 1, "vectors": []}

data/ulwa json corpus/speakers.json

@@ -0,0 +1 @@
+{"Tang": {"meta": {}, "vectors": []}, "Yan": {"meta": {}, "vectors": []}}

data/ulwa json corpus/utterances.jsonl

@@ -0,0 +1,10 @@
+{"id": "0", "conversation_id": "/ulwa1/ulwa014", "text": "U oughs inim t\u00ef samting yan", "speaker": "Tang", "meta": {}, "reply-to": null, "timestamp": 1332718704, "vectors": []}
+{"id": "1", "conversation_id": "/ulwa1/ulwa014", "text": "mbam ndul ma wandam ana", "speaker": "Yan", "meta": {}, "reply-to": null, "timestamp": 1332732704, "vectors": []}
+{"id": "2", "conversation_id": "/ulwa1/ulwa014", "text": "M\u00ef inim wandam bai anapa nd", "speaker": "Tang", "meta": {}, "reply-to": null, "timestamp": 1332743704, "vectors": []}
+{"id": "3", "conversation_id": "/ulwa1/ulwa014", "text": "lunda we nd\u00efm\u00efne in", "speaker": "Yan", "meta": {}, "reply-to": null, "timestamp": 1332754704, "vectors": []}
+{"id": "4", "conversation_id": "/ulwa1/ulwa014", "text": "k\u00efnakape ak\u00efnaka", "speaker": "Tang", "meta": {}, "reply-to": null, "timestamp": 1332765704, "vectors": []}
+{"id": "5", "conversation_id": "/ulwa1/ulwa014", "text": "coughs nd\u00efm\u00efne we ndul wa le we nd\u00eft\u00ef ak\u00efnakape malimap mat\u00ef yawa mananda", "speaker": "Yan", "meta": {}, "reply-to": null, "timestamp": 1332776704, "vectors": []}
+{"id": "6", "conversation_id": "/ulwa1/ulwa014", "text": "mananda", "speaker": "Tang", "meta": {}, "reply-to": null, "timestamp": 1332787704, "vectors": []}
+{"id": "7", "conversation_id": "/ulwa1/ulwa014", "text": "da", "speaker": "Yan", "meta": {}, "reply-to": null, "timestamp": 1332788704, "vectors": []}
+{"id": "8", "conversation_id": "/ulwa1/ulwa014", "text": "e k\u00efkal awi ak\u00efnakape", "speaker": "Tang", "meta": {}, "reply-to": null, "timestamp": 1332789704, "vectors": []}
+{"id": "9", "conversation_id": "/ulwa1/ulwa014", "text": "at\u00efm inim.", "speaker": "Yan", "meta": {}, "reply-to": null, "timestamp": 1332999704, "vectors": []}

data/ulwa_testdata_convokit_format.csv

@@ -0,0 +1,11 @@
+timestamp,speaker,text,translation,conversation_id,utterance_raw,reply_to
+1332718704,Tang,U oughs inim tï samting yan,"Lorem ipsum dolor sit amet.",/ulwa1/ulwa014,U oughs inim tï samting yangama ul matï akïnakape,None
+1332732704,Yan,mbam ndul ma wandam ana,"At neque fugit eum reprehenderit labore et exercitationem voluptatem.  eos odio aspernatur.",/ulwa1/ulwa014,wimbam ndul ma wandam anapa ol welunda nïkap tu mananda yangama,None
+1332743704,Tang,Mï inim wandam bai anapa nd,"a veritatis tempore sit vitae quaerat sed consequatur amet qui nisi facilis et perferendis nisi ut maiores consequatur.",/ulwa1/ulwa014,Mï inim wandam bai anapa ndïtï ka welunda unan,None
+1332754704,Yan,lunda we ndïmïne in,,/ulwa1/ulwa014,ata welunda we ndïmïne ind,None
+1332765704,Tang,kïnakape akïnaka,,/ulwa1/ulwa014,i akïnakape akïnakap,None
+1332776704,Yan,coughs ndïmïne we ndul wa le we ndïtï akïnakape malimap matï yawa mananda,"Et illo facere vel magni necessitatibus est aspernatur numquam",/ulwa1/ulwa014,[coughs] I inim oughs ka lopop mananda bai kïkal yangama we ini,None
+1332787704,Tang,mananda,,/ulwa1/ulwa014,n mananda ndïtï ka akïnakape wimbam,None
+1332788704,Yan,da,,/ulwa1/ulwa014,da ndïtï ka,None
+1332789704,Tang,e kïkal awi akïnakape,"onsequatur amet qui nisi facilis et perferendis nisi ut",/ulwa1/ulwa014,e kïkal awi akïnakape manï lï,None
+1332999704,Yan,atïm inim.,"itae quaerat sed consequatur amet",/ulwa1/ulwa014,atïm inim.,None

data/ulwa_testdata_sktalk_format.csv

@@ -0,0 +1,11 @@
+begin,end,participant,utterance,translation,source,utterance_raw
+00:00:00.917,00:00:05.604,Tang,U oughs inim tï samting yan,"Lorem ipsum dolor sit amet.",/ulwa1/ulwa014,U oughs inim tï samting yangama ul matï akïnakape
+00:00:04.830,00:00:09.080,Yan,mbam ndul ma wandam ana,"At neque fugit eum reprehenderit labore et exercitationem voluptatem.  eos odio aspernatur.",/ulwa1/ulwa014,wimbam ndul ma wandam anapa ol welunda nïkap tu mananda yangama 
+00:00:06.090,00:00:09.450,Tang,Mï inim wandam bai anapa nd,"a veritatis tempore sit vitae quaerat sed consequatur amet qui nisi facilis et perferendis nisi ut maiores consequatur.",/ulwa1/ulwa014,Mï inim wandam bai anapa ndïtï ka welunda unan
+00:00:09.534,00:00:10.333,Yan,lunda we ndïmïne in,,/ulwa1/ulwa014,ata welunda we ndïmïne ind
+00:00:10.333,00:00:11.143,Tang,kïnakape akïnaka,,/ulwa1/ulwa014,i akïnakape akïnakap
+00:00:11.143,00:00:18.240,Yan,coughs ndïmïne we ndul wa le we ndïtï akïnakape malimap matï yawa mananda,"Et illo facere vel magni necessitatibus est aspernatur numquam",/ulwa1/ulwa014,[coughs] I inim oughs ka lopop mananda bai kïkal yangama we ini
+00:00:11.477,00:00:12.205,Tang,mananda,,/ulwa1/ulwa014,n mananda ndïtï ka akïnakape wimbam
+00:00:14.390,00:00:15.696,Yan,da,,/ulwa1/ulwa014,da ndïtï ka
+00:00:17.972,00:00:20.722,Tang,e kïkal awi akïnakape,"onsequatur amet qui nisi facilis et perferendis nisi ut",/ulwa1/ulwa014,e kïkal awi akïnakape manï lï
+00:00:18.240,00:00:21.970,Yan,atïm inim.,"itae quaerat sed consequatur amet",/ulwa1/ulwa014,atïm inim.

data/vamale json corpus/conversations.json

@@ -0,0 +1 @@
+{"/vamale1/vamaleE": {"meta": {}, "vectors": []}, "/vamale1/vamaleie": {"meta": {}, "vectors": []}, "/vamale1/vamale-vie": {"meta": {}, "vectors": []}, "/vamale1/vamale-MS": {"meta": {}, "vectors": []}, "/vamale1/vamaleMS": {"meta": {}, "vectors": []}, "/vamale1/vamalen-MS": {"meta": {}, "vectors": []}, "/vamale1/vamale4": {"meta": {}, "vectors": []}}

data/vamale json corpus/corpus.json

@@ -0,0 +1 @@
+{}

data/vamale json corpus/index.json

@@ -0,0 +1 @@
+{"utterances-index": {}, "speakers-index": {}, "conversations-index": {}, "overall-index": {}, "version": 1, "vectors": []}

data/vamale json corpus/speakers.json

@@ -0,0 +1 @@
+{"Ric": {"meta": {}, "vectors": []}, "Rie": {"meta": {}, "vectors": []}}

data/vamale json corpus/utterances.jsonl

@@ -0,0 +1,10 @@
+{"id": "0", "conversation_id": "/vamale1/vamaleE", "text": "Aoo angovi \u0263ase aoo vinjo thamauke va nyau yanle?", "speaker": "Ric", "meta": {}, "reply-to": null, "timestamp": 1332712704, "vectors": []}
+{"id": "1", "conversation_id": "/vamale1/vamaleie", "text": "ta\u0263ua va thamauke \u0272akoe va angovi \u0263ase.", "speaker": "Rie", "meta": {}, "reply-to": null, "timestamp": 1332722704, "vectors": []}
+{"id": "2", "conversation_id": "/vamale1/vamale-vie", "text": "Va vinjo ta\u0263ua daa thanga \u0272akoe daa \u0263ase angovi", "speaker": "Ric", "meta": {}, "reply-to": null, "timestamp": 1332732704, "vectors": []}
+{"id": "3", "conversation_id": "/vamale1/vamale-MS", "text": "a nyau thapoke va \u0272akoe", "speaker": "Rie", "meta": {}, "reply-to": null, "timestamp": 1332742704, "vectors": []}
+{"id": "4", "conversation_id": "/vamale1/vamaleMS", "text": "\u0272akoe va \u0263ananda konaa va \u0263ananda vinjo ", "speaker": "Ric", "meta": {}, "reply-to": null, "timestamp": 1332755704, "vectors": []}
+{"id": "5", "conversation_id": "/vamale1/vamaleMS", "text": "o \u0263ase va angovi angovi nea", "speaker": "Rie", "meta": {}, "reply-to": null, "timestamp": 1332766704, "vectors": []}
+{"id": "6", "conversation_id": "/vamale1/vamalen-MS", "text": "au nyau aoo thamauke \u0263ase daa ya", "speaker": "Ric", "meta": {}, "reply-to": null, "timestamp": 1332777704, "vectors": []}
+{"id": "7", "conversation_id": "/vamale1/vamaleMS", "text": "uke! Daa \u0263ananda thamauke va \u0263ase t", "speaker": "Rie", "meta": {}, "reply-to": null, "timestamp": 1332788804, "vectors": []}
+{"id": "8", "conversation_id": "/vamale1/vamale4", "text": "yanle konaa daa thamauke \u0263ananda va", "speaker": "Ric", "meta": {}, "reply-to": null, "timestamp": 1332799904, "vectors": []}
+{"id": "9", "conversation_id": "/vamale1/vamale4", "text": "ga nyau va vinjo konaa daa \u0263anand", "speaker": "Rie", "meta": {}, "reply-to": null, "timestamp": 1332792704, "vectors": []}

data/vamale_testdata_convokit_format.csv

@@ -0,0 +1,11 @@
+timestamp,speaker,text,conversation_id,utterance_raw,reply_to
+1332712704,Ric,Aoo angovi ɣase aoo vinjo thamauke va nyau yanle?,/vamale1/vamaleE,Aoo angovi ɣase aoo vinjo thamauke va nyau yanle?,None
+1332722704,Rie,taɣua va thamauke ɲakoe va angovi ɣase.,/vamale1/vamaleie,ua va thamauke ɲakoe v,None
+1332732704,Ric,Va vinjo taɣua daa thanga ɲakoe daa ɣase angovi,/vamale1/vamale-vie,aa thanga ɲakoe daa ɣase,None
+1332742704,Rie,a nyau thapoke va ɲakoe,/vamale1/vamale-MS,thapoke va ɲak,None
+1332755704,Ric,ɲakoe va ɣananda konaa va ɣananda vinjo ,/vamale1/vamaleMS,ɣnaa va ɣananda vin,None
+1332766704,Rie,o ɣase va angovi angovi nea,/vamale1/vamaleMS,va angovi angovi,None
+1332777704,Ric,au nyau aoo thamauke ɣase daa ya,/vamale1/vamalen-MS,limyau aoo thamauke ɣase daaa,None
+1332788804,Rie,uke! Daa ɣananda thamauke va ɣase t,/vamale1/vamaleMS,ke! Daa ɣananda tham,None
+1332799904,Ric,yanle konaa daa thamauke ɣananda va,/vamale1/vamale4,konaa daa,None
+1332792704,Rie,ga nyau va vinjo konaa daa ɣanand,/vamale1/vamale4,au va vinjo konaa daa ɣa,None

data/vamale_testdata_sktalk_format.csv

@@ -0,0 +1,11 @@
+begin,end,participant,utterance,translation,source,utterance_raw
+00:01:33.740,00:01:36.200,Ric,Aoo angovi ɣase aoo vinjo thamauke va nyau yanle?,,/vamale1/vamaleE,Aoo angovi ɣase aoo vinjo thamauke va nyau yanle?
+00:02:25.065,00:02:26.445,Rie,taɣua va thamauke ɲakoe va angovi ɣase.,,/vamale1/vamaleie,ua va thamauke ɲakoe v
+00:02:26.385,00:02:27.925,Ric,Va vinjo taɣua daa thanga ɲakoe daa ɣase angovi,,/vamale1/vamale-vie,aa thanga ɲakoe daa ɣase
+00:03:03.530,00:03:05.130,Rie,a nyau thapoke va ɲakoe,,/vamale1/vamale-MS,thapoke va ɲak
+00:03:05.595,00:03:08.355,Ric,ɲakoe va ɣananda konaa va ɣananda vinjo ,,/vamale1/vamaleMS,ɣnaa va ɣananda vin
+00:03:08.710,00:03:12.720,Rie,o ɣase va angovi angovi nea,,/vamale1/vamaleMS,va angovi angovi
+00:03:12.950,00:03:16.760,Ric,au nyau aoo thamauke ɣase daa ya,,/vamale1/vamalen-MS,limyau aoo thamauke ɣase daaa
+00:03:17.070,00:03:19.470,Rie,uke! Daa ɣananda thamauke va ɣase t,,/vamale1/vamaleMS,ke! Daa ɣananda tham
+00:15:44.815,00:15:46.395,Ric,yanle konaa daa thamauke ɣananda va,,/vamale1/vamale4,konaa daa
+00:26:03.605,00:26:05.345,Rie,ga nyau va vinjo konaa daa ɣanand,,/vamale1/vamale4,au va vinjo konaa daa ɣa