forced_alignment_novo.py is removed (.gitignore). commit history is cleaned up.

.gitignore

@@ -1,6 +1,9 @@
 ## Ignore Visual Studio temporary files, build results, and
 ## files generated by popular Visual Studio add-ons.
 
+## important ##
+.acoustic_model/forced_alignment_novo.py
+
 # User-specific files
 *.suo
 *.user

acoustic_model/check_novoapi.py

@@ -25,14 +25,32 @@ mapping = convert_xsampa2ipa.load_converter('xsampa', 'ipa', default.ipa_xsampa_
 
 stimmen_transcription_ = pd.ExcelFile(default.stimmen_transcription_xlsx)
 
-phonelist_novo70_      = pd.ExcelFile(default.phonelist_novo70_xlsx)
-df = pd.read_excel(phonelist_novo70_, 'list')
 
+## novo phoneset
 translation_key = dict()
-for ipa, novo70 in zip(df['IPA_simple'], df['novo70_simple']):
-    if not pd.isnull(ipa):
-        print('{0}:{1}'.format(ipa, novo70))
-        translation_key[ipa] = novo70
 
-#df = pd.read_excel(stimmen_transcription, 'check')
+#phonelist_novo70_      = pd.ExcelFile(default.phonelist_novo70_xlsx)
+#df = pd.read_excel(phonelist_novo70_, 'list')
+## *_simple includes columns which has only one phone in.
+#for ipa, novo70 in zip(df['IPA_simple'], df['novo70_simple']):
+#    if not pd.isnull(ipa):
+#        print('{0}:{1}'.format(ipa, novo70))
+#        translation_key[ipa] = novo70
+#phonelist_novo70 = np.unique(list(df['novo70_simple']))
+
+phoneset_ipa = []
+phoneset_novo70 = []
+with open(default.cmu69_phoneset, "rt", encoding="utf-8") as fin:
+	lines = fin.read()
+	lines = lines.split('\n')
+	for line in lines:
+		words = line.split('\t')
+		if len(words) > 1:
+			novo70 = words[0]
+			ipa	   = words[1]
+			phoneset_ipa.append(ipa)
+			phoneset_novo70.append(novo70)
+			translation_key[ipa] = novo70
+phoneset_ipa    = np.unique(phoneset_ipa)
+phoneset_novo70 = np.unique(phoneset_novo70)
 

acoustic_model/defaultfiles.py

@@ -3,7 +3,7 @@ import os
 #default_hvite_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), 'data', 'htk', 'config.HVite')
 
 cygwin_dir = r'C:\cygwin64\home\Aki\acoustic_model'
-kaldi_dir = r'C:\OneDrive\WSL\kaldi-trunk\egs\fame\s5'
+
 #config_hcopy = os.path.join(cygwin_dir, 'config', 'config.HCopy')
 #config_train = os.path.join(cygwin_dir, 'config', 'config.train')
 config_hvite = os.path.join(cygwin_dir, 'config', 'config.HVite')
@@ -30,11 +30,15 @@ repo_dir = r'C:\Users\Aki\source\repos'
 ipa_xsampa_converter_dir    = os.path.join(repo_dir, 'ipa-xsama-converter')
 forced_alignment_module_dir = os.path.join(repo_dir, 'forced_alignment')
 
-fame_dir        = r'C:\OneDrive\WSL\kaldi-trunk\egs\fame\s5\corpus'
+WSL_dir   = r'C:\OneDrive\WSL'
+fame_dir        = os.path.join(WSL_dir, 'kaldi-trunk', 'egs', 'fame')
+fame_s5_dir     = os.path.join(fame_dir, 's5')
+fame_corpus_dir = os.path.join(fame_dir, 'corpus')
 
 experiments_dir = r'c:\OneDrive\Research\rug\experiments'
 stimmen_transcription_xlsx = os.path.join(experiments_dir, 'stimmen', 'data', 'Frisian Variants Picture Task Stimmen.xlsx')
 stimmen_data_dir           = os.path.join(experiments_dir, 'stimmen', 'data')
 phonelist_friesian_txt     = os.path.join(experiments_dir, 'friesian', 'acoustic_model', 'config', 'phonelist_friesian.txt')
-phonelist_novo70_xlsx      = os.path.join(experiments_dir, 'Nederlandse phonesets_aki.xlsx')
 
+novo_api_dir = os.path.join(WSL_dir, 'python-novo-api')
+cmu69_phoneset = os.path.join(novo_api_dir, 'novoapi', 'asr', 'phoneset', 'en', 'cmu69.phoneset')