def fave_corpus_config(graph_db, fave_test_dir):
config = CorpusConfig('fave_test_corpus', **graph_db)
with CorpusContext(config) as c:
c.reset()
parser = inspect_fave(fave_test_dir)
c.load(parser, fave_test_dir)
return config
def partitur_corpus_config(graph_db, partitur_test_dir):
config = CorpusConfig('partitur', **graph_db)
partitur_path = os.path.join(partitur_test_dir, 'partitur_test.par,2')
with CorpusContext(config) as c:
c.reset()
parser = inspect_partitur(partitur_path)
c.load(parser, partitur_path)
return config
def stressed_config(graph_db, textgrid_test_dir):
config = CorpusConfig('stressed', **graph_db)
stressed_path = os.path.join(textgrid_test_dir, 'stressed_corpus.TextGrid')
with CorpusContext(config) as c:
c.reset()
parser = inspect_mfa(stressed_path)
c.load(parser, stressed_path)
return config
def subannotation_config(graph_db, subannotation_data):
config = CorpusConfig('subannotations', **graph_db)
with CorpusContext(config) as c:
c.reset()
c.add_types(*subannotation_data.types('subannotations'))
c.initialize_import()
c.add_discourse(subannotation_data)
c.finalize_import()
return config
def ursr_config(graph_db, corpus_data_ur_sr):
config = CorpusConfig('ur_sr', **graph_db)
with CorpusContext(config) as c:
c.reset()
c.add_types(*corpus_data_ur_sr.types('ur_sr'))
c.initialize_import()
c.add_discourse(corpus_data_ur_sr)
c.finalize_import()
return config
def timed_config(graph_db, corpus_data_timed):
config = CorpusConfig('timed', **graph_db)
with CorpusContext(config) as c:
c.reset()
c.add_types(*corpus_data_timed.types('timed'))
c.initialize_import()
c.add_discourse(corpus_data_timed)
c.finalize_import()
return config
def summarized_config(graph_db, textgrid_test_dir):
config = CorpusConfig('summarized', **graph_db)
acoustic_path = os.path.join(textgrid_test_dir, 'acoustic_corpus.TextGrid')
with CorpusContext(config) as c:
c.reset()
parser = inspect_textgrid(acoustic_path)
c.load(parser, acoustic_path)
return config
def syllable_morpheme_config(graph_db, corpus_data_syllable_morpheme_srur):
config = CorpusConfig('syllable_morpheme', **graph_db)
with CorpusContext(config) as c:
c.reset()
c.add_types(
*corpus_data_syllable_morpheme_srur.types('syllable_morpheme'))
c.initialize_import()
c.add_discourse(corpus_data_syllable_morpheme_srur)
c.finalize_import()
return config
def acoustic_config(graph_db, textgrid_test_dir):
config = CorpusConfig('acoustic', **graph_db)
acoustic_path = os.path.join(textgrid_test_dir, 'acoustic_corpus.TextGrid')
with CorpusContext(config) as c:
c.reset()
parser = inspect_textgrid(acoustic_path)
c.load(parser, acoustic_path)
config.pitch_algorithm = 'acousticsim'
config.formant_source = 'acousticsim'
return config
def ursr_config(graph_db, corpus_data_ur_sr):
config = CorpusConfig('ur_sr', **graph_db)
with CorpusContext(config) as c:
c.reset()
c.add_types(*corpus_data_ur_sr.types('ur_sr'))
c.initialize_import(corpus_data_ur_sr.speakers,
corpus_data_ur_sr.token_headers,
corpus_data_ur_sr.hierarchy.subannotations)
c.add_discourse(corpus_data_ur_sr)
c.finalize_import(corpus_data_ur_sr)
return config
def syllable_morpheme_config(graph_db, corpus_data_syllable_morpheme_srur):
config = CorpusConfig('syllable_morpheme', **graph_db)
with CorpusContext(config) as c:
c.reset()
c.add_types(*corpus_data_syllable_morpheme_srur.types('syllable_morpheme'))
c.initialize_import(corpus_data_syllable_morpheme_srur.speakers,
corpus_data_syllable_morpheme_srur.token_headers,
corpus_data_syllable_morpheme_srur.hierarchy.subannotations)
c.add_discourse(corpus_data_syllable_morpheme_srur)
c.finalize_import(corpus_data_syllable_morpheme_srur)
return config
def timed_config(graph_db, corpus_data_timed):
config = CorpusConfig('timed', **graph_db)
with CorpusContext(config) as c:
c.reset()
c.add_types(*corpus_data_timed.types('timed'))
c.initialize_import(corpus_data_timed.speakers,
corpus_data_timed.token_headers,
corpus_data_timed.hierarchy.subannotations)
c.add_discourse(corpus_data_timed)
c.finalize_import(corpus_data_timed)
return config
def french_config(graph_db, textgrid_test_dir):
config = CorpusConfig('french', **graph_db)
french_path = os.path.join(textgrid_test_dir, 'FR001_5.TextGrid')
with CorpusContext(config) as c:
c.reset()
parser = inspect_textgrid(french_path)
c.load(parser, french_path)
c.encode_pauses(['sil', '<SIL>'])
c.encode_utterances(min_pause_length=.15)
return config
def subannotation_config(graph_db, subannotation_data):
config = CorpusConfig('subannotations', **graph_db)
with CorpusContext(config) as c:
c.reset()
c.add_types(*subannotation_data.types('subannotations'))
c.initialize_import(subannotation_data.speakers,
subannotation_data.token_headers,
subannotation_data.hierarchy.subannotations)
c.add_discourse(subannotation_data)
c.finalize_import(subannotation_data.speakers,
subannotation_data.token_headers,
subannotation_data.hierarchy)
return config
def acoustic_utt_config(graph_db, textgrid_test_dir):
config = CorpusConfig('acoustic utt', **graph_db)
acoustic_path = os.path.join(textgrid_test_dir, 'acoustic_corpus.TextGrid')
with CorpusContext(config) as c:
c.reset()
parser = inspect_textgrid(acoustic_path)
c.load(parser, acoustic_path)
c.encode_pauses(['sil'])
c.encode_utterances(min_pause_length=0)
config.pitch_algorithm = 'acousticsim'
config.formant_algorithm = 'acousticsim'
return config
def overlapped_config(graph_db, textgrid_test_dir, acoustic_syllabics):
config = CorpusConfig('overlapped', **graph_db)
acoustic_path = os.path.join(textgrid_test_dir, 'overlapped_speech')
with CorpusContext(config) as c:
c.reset()
parser = inspect_mfa(acoustic_path)
c.load(parser, acoustic_path)
c.encode_pauses(['sil'])
c.encode_utterances(min_pause_length=0)
c.encode_syllabic_segments(acoustic_syllabics)
c.encode_syllables()
config.pitch_algorithm = 'acousticsim'
config.formant_source = 'acousticsim'
return config
