pelican-nlp 0.1.1__py3-none-any.whl → 0.1.2__py3-none-any.whl

pelican_nlp/configuration_files/config_fluency.yml

@@ -0,0 +1,108 @@
+# Configuration file for fluency task
+# =======================================
+input_file: "text" #or 'audio'
+fluency_task: &fluency_flag true
+#========================================
+
+#general configurations; always adapt
+PATH_TO_PROJECT_FOLDER: "/home/yvespauli/PycharmProjects/FluencyTest"
+language: "german"
+multiple_sessions: &session_flag false
+
+corpus_names: #names of fluency tasks (e.g. "animals", "clothes")
+  - "animals"
+  - "clothes"
+  - "food"
+
+#Specify linguistic metrics to extract
+metric_to_extract: 'embeddings' #Possible options: 'embeddings', 'logits'
+output_document_information: true
+#====================================================================
+
+#Optional configurations; Change with preference. However, default settings recommended
+cleaning_options:
+  general_cleaning: true
+  #Options for fluency tasks
+  fluency_task: *fluency_flag
+  word_splitter: ';' #default split with ',' add different word_splitter if necessary
+  remove_hyphens: true
+  remove_duplicates: false
+  lowercase: false
+  #Optional cleaning
+  remove_brackets_and_bracketcontent: false #default 'false'
+  remove_timestamps: false #default 'false'
+  timestamp_pattern_example: null #e.g. "#00:00:23-00#"
+  remove_punctuation: false #Careful!: If set to true word_splitter might be removed
+
+options_embeddings:
+  tokenization_method: "whitespace" #or "model"
+  model_name: "fastText" #e.g. "fastText", "xlm-roberta-base"
+  pytorch_based_model: false
+  method: "model_instance"
+  max_length: null
+  clean_embedding_tokens: true
+
+  semantic-similarity: true
+  distance-from-randomness: false
+
+options_dis_from_randomness:
+  window_size: 8
+  min_len: null
+  bootstrap: 10000
+  shuffle_mode: 'include0_includeN'
+  parallel_computing: false #not yet set up
+
+options_semantic-similarity:
+  window_sizes: #'all' or window size as integer
+    - 2
+    - 8
+#==================================================================
+
+#Extra configurations;
+task_name: "fluency"
+create_aggregation_of_results: true
+
+pipeline_options:
+  quality_check: false
+  clean_text: true
+  tokenize_text: false
+  normalize_text: false
+
+general_cleaning_options:
+  strip_whitespace: true
+  merge_multiple_whitespaces: true
+  remove_whitespace_before_punctuation: true
+  merge_newline_characters: true
+  remove_backslashes: true
+
+has_multiple_sections: false
+has_section_titles: false
+section_identification: null
+number_of_sections: 1
+number_of_speakers: 1
+discourse: false
+
+document_information_output:
+  parameters:
+    - subject_ID
+    - fluency_word_count
+    - fluency_duplicate_count
+
+#================================================================
+
+#Detail configurations; Changes optional, mostly used for quality checking / error handling
+recompute_everything: true
+number_of_subjects: null
+
+# Filename components configuration
+filename_components:
+  subject: true    # mandatory
+  session: *session_flag
+  task: true       # mandatory
+  task_addition: false
+  corpus: true    # typically true for fluency tasks (e.g., "animals", "clothes")
+  metric: true
+  additional_tags: []
+
+
+

pelican_nlp/configuration_files/config_general.yml

@@ -0,0 +1,131 @@
+# Master Configuration File
+# ========================
+
+# Basic Settings
+# -------------
+input_file: "text"  # Options: 'text' or 'audio'
+PATH_TO_PROJECT_FOLDER: "/home/yvespauli/PycharmProjects/FluencyTest"
+language: "german"  # Options: 'german', 'english'
+recompute_everything: true  # If false, reuses previously computed results
+
+# Task Configuration
+# -----------------
+task_name: "fluency"  # Options: 'fluency', 'interview'
+fluency_task: &fluency_flag true  # Flag for fluency-specific settings
+discourse: &discourse_flag false  # Flag for discourse-specific settings
+corpus_names:  # List of task corpora
+  - "animals"
+
+# Session and Subject Settings
+# --------------------------
+multiple_sessions: false
+number_of_subjects: null  # If null, auto-detected
+number_of_speakers: 1
+subject_speakertag: null  # Speaker tag for subject (e.g., "B")
+
+# Document Structure
+# ----------------
+has_multiple_sections: false
+has_section_titles: false
+section_identification: null  # e.g., "Section:"
+number_of_sections: 1  # If null, auto-detected
+
+# Processing Pipeline
+# -----------------
+pipeline_options:
+  quality_check: false
+  clean_text: true
+  tokenize_text: false
+  normalize_text: false
+
+# Metric Extraction
+# ---------------
+metric_to_extract: "embeddings"  # Options: 'embeddings', 'logits'
+extract_logits: null
+extract_embeddings: true
+
+# Cleaning Options
+# --------------
+cleaning_options:
+  general_cleaning: true
+  remove_punctuation: false
+  lowercase: true
+  remove_brackets_and_bracketcontent: false
+  remove_timestamps: false
+  timestamp_pattern_example: null  # e.g., "#00:00:23-00#"
+  # Fluency-specific options
+  fluency_task: *fluency_flag
+  word_splitter: ';'
+  remove_hyphens: true
+  remove_duplicates: true
+
+general_cleaning_options:
+  strip_whitespace: true
+  merge_multiple_whitespaces: true
+  remove_whitespace_before_punctuation: true
+  merge_newline_characters: true
+  remove_backslashes: true
+
+# Embedding Options
+# ---------------
+options_embeddings:
+  tokenization_method: "whitespace"  # Options: 'whitespace', 'model'
+  model_name: "fastText"  # Options: 'fastText', 'xlm-roberta-base'
+  pytorch_based_model: false
+  method: "model_instance"
+  max_length: 512
+  clean_embedding_tokens: true
+  remove_punctuation: false
+  lowercase: false
+  keep_speakertags: false
+  semantic-similarity: true
+  window_size: null
+  clean_tokens: true
+  divergence_from_optimality: false
+  output_options:
+    exclude_special_tokens: true
+    remove_'_'_character: true
+    remove_speaker_labels: true
+    remove_punctuation_and_symbols: true
+    remove_brackets_and_content: true
+
+# Logits Options
+# -------------
+options_logits:
+  chunk_size: 128
+  overlap_size: 64
+  tokenization_method: "model"
+  model_name: "DiscoResearch/Llama3-German-8B-32k"
+  remove_punctuation: true
+  lowercase: true
+  keep_speakertags: true
+
+# Analysis Options
+# --------------
+options_semantic-similarity:
+  window_sizes:  # 'all' or window size as integer
+    - 2
+    - 8
+
+options_dis_from_randomness:
+  window_size: 8
+  min_len: null
+  bootstrap: 10000
+  shuffle_mode: 'include0_includeN'
+  parallel_computing: false
+
+# Normalization Options
+# -------------------
+normalization_options:
+  method: "lemmatization"  # Options: 'lemmatization', 'stemming'
+
+# Filename Configuration
+# --------------------
+filename_components:
+  subject: true    # mandatory
+  session: false
+  task: true       # mandatory
+  task_addition: false
+  corpus: true
+  metric: true
+  additional_tags: []

pelican_nlp/configuration_files/config_morteza.yml

@@ -0,0 +1,103 @@
+# Configuration file: variable parameters
+# =======================================
+input_file: "text" #or 'audio'
+discourse: &discourse_flag true
+
+#PATH_TO_PROJECT_FOLDER: "/home/yvespauli/PycharmProjects/KetamineStudy/KetamineStudy_ProjectFolder/" # Set default to home directory, e.g., '/home/usr/...'
+PATH_TO_PROJECT_FOLDER: "/home/yvespauli/PycharmProjects/Morteza/"
+language: "german" # Possibly add options for German and English
+
+task_name: "interview" # Give name of task used for creation of the input file (e.g., ['fluency', 'interview'])
+corpus_names:
+  - "schizophrenia"
+
+
+number_of_subjects: null # Specify number of subjects; if 'null', number of subjects is automatically detected
+multiple_sessions: false # Set to True if multiple sessions per subject
+
+recompute_everything: true #If set to 'false' pelican-nlp will try to reuse previously computed results stored on your drive
+
+has_multiple_sections: false #evaluated independently
+has_section_titles: false
+section_identification: null #e.g. "Section:", 'null' if file does not have multiple sections, use pattern that is unlikely to appear in rest of transcript
+number_of_sections: null #if 'null' number of sections automatically detected, however, specifying number recommended if known.
+
+number_of_speakers: 3
+subject_speakertag: "B"
+
+metric_to_extract: "embeddings"
+extract_logits: false
+extract_embeddings: true
+
+pipeline_options:
+  quality_check: false
+  clean_text: true
+  tokenize_text: false
+  normalize_text: false
+
+tokenization: "wordLevel" # Options: 'characterLevel', 'subWordLevel'
+
+# Options for extract_logits
+chunk_size: null
+overlap_size: null
+
+# Options for extract_embeddings
+window_sizes: [2]
+metric_function: cosine_similarity
+aggregation_functions: mean_of_means
+
+
+fluency_task: &fluency_flag false
+cleaning_options:
+  general_cleaning: true # General cleaning options used for most text preprocessing, default: True.
+  remove_brackets_and_bracketcontent: true
+  remove_timestamps: true
+  timestamp_pattern_example: "#00:00:19-0#"
+  #Options for fluency tasks
+  fluency_task: *fluency_flag
+  word_splitter: null
+  remove_hyphens: null
+  remove_duplicates: null
+
+general_cleaning_options:
+  strip_whitespace: true
+  merge_multiple_whitespaces: true
+  remove_whitespace_before_punctuation: true
+  merge_newline_characters: true
+  remove_backslashes: true
+
+tokenization_options_logits:
+  method: "model_instance" # Options: model_instance, regex, nltk, etc.
+  model_name: "DiscoResearch/Llama3-German-8B-32k" # Replace with your model instance name
+  remove_punctuation: true
+  lowercase: true
+
+options_embeddings:
+  tokenization_method: "model_roberta" #or "whitespace", "model"
+  max_length: 512 #max sequence length
+  model_name: "xlm-roberta-base" #e.g. "fastText", "xlm-roberta-base"
+  pytorch_based_model: true
+  method: "model_instance"
+  remove_punctuation: false
+  lowercase: false
+  keep_speakertags: true
+  clean_embedding_tokens: true
+  output_options:
+    exclude_special_tokens: true
+    remove_'_'_character: true
+    remove_speaker_labels: true
+    remove_punctuation_and_symbols: true
+    remove_brackets_and_content: true
+
+  window_size: null
+
+  semantic-similarity: false
+  distance-from-randomness: false
+
+normalization_options:
+  method: "lemmatization" #Options: lemmatization or stemming
+
+create_aggregation_of_results: false
+output_document_information: false
+
+

pelican_nlp/praat/__init__.py

@@ -0,0 +1,29 @@
+import os
+
+# Get the directory where the Praat scripts are stored
+PRAAT_SCRIPTS_DIR = os.path.dirname(os.path.abspath(__file__))
+
+# Define paths to individual scripts
+PROSOMAIN_SCRIPT = os.path.join(PRAAT_SCRIPTS_DIR, 'prosomain.praat')
+PROSOGRAM_SCRIPT = os.path.join(PRAAT_SCRIPTS_DIR, 'prosogram.praat')
+PROSOPLOT_SCRIPT = os.path.join(PRAAT_SCRIPTS_DIR, 'prosoplot.praat')
+SEGMENT_SCRIPT = os.path.join(PRAAT_SCRIPTS_DIR, 'segment.praat')
+STYLIZE_SCRIPT = os.path.join(PRAAT_SCRIPTS_DIR, 'stylize.praat')
+POLYTONIA_SCRIPT = os.path.join(PRAAT_SCRIPTS_DIR, 'polytonia.praat')
+UTIL_SCRIPT = os.path.join(PRAAT_SCRIPTS_DIR, 'util.praat')
+EPS_CONV_SCRIPT = os.path.join(PRAAT_SCRIPTS_DIR, 'eps_conv.praat')
+SETUP_SCRIPT = os.path.join(PRAAT_SCRIPTS_DIR, 'setup.praat')
+
+# Export all script paths
+__all__ = [
+    'PRAAT_SCRIPTS_DIR',
+    'PROSOMAIN_SCRIPT',
+    'PROSOGRAM_SCRIPT',
+    'PROSOPLOT_SCRIPT',
+    'SEGMENT_SCRIPT',
+    'STYLIZE_SCRIPT',
+    'POLYTONIA_SCRIPT',
+    'UTIL_SCRIPT',
+    'EPS_CONV_SCRIPT',
+    'SETUP_SCRIPT'
+]

{pelican_nlp-0.1.1.dist-info → pelican_nlp-0.1.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pelican_nlp
-Version: 0.1.1
+Version: 0.1.2
 Summary: Preprocessing and Extraction of Linguistic Information for Computational Analysis
 Author-email: Yves Pauli <yves.pauli@gmail.com>
 License-Expression: CC-BY-NC-4.0
@@ -75,7 +75,7 @@ For the latest development version:
 
 .. code-block:: bash
 
-    pip install git+https://github.com/ypauli/PELICAN_nlp.git
+    pip install https://github.com/yourusername/yourrepo/releases/tag/v0.1.0-alpha
 
 Usage
 =====
@@ -107,7 +107,8 @@ Text and audio files should follow this naming convention:
 - extension: file extension (e.g., txt / pdf / docx / rtf), mandatory
 
 Example filenames:
-- sub-01_ses-01_interview_schizophrenia.rtf
+
+- sub-01_interview_schizophrenia.rtf
 - sub-03_ses-02_fluency_semantic_animals.docx
 
 To optimize performance, close other programs and limit GPU usage during language processing.

pelican_nlp-0.1.2.dist-info/RECORD

@@ -0,0 +1,75 @@
+pelican_nlp/__init__.py,sha256=TD5xjKeXXAH6nUWG-6igbClgovi5r8RIEqI_ix1QeYo,204
+pelican_nlp/_version.py,sha256=K5SiDdEGYMpdqXThrqwTqECJJBOQNTQDrnpc2K5mzKs,21
+pelican_nlp/main.py,sha256=xKUqqA3sh9kbk07lKA_poILIU1c8oIeaSsVqPOPY5Tk,7596
+pelican_nlp/Nils_backup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pelican_nlp/Nils_backup/extract_acoustic_features.py,sha256=eSP8lXxbZ15YE1HqxGtma9uWOcSN-fI-ig-NwQ9eOA8,10771
+pelican_nlp/Nils_backup/speaker_diarization_Nils.py,sha256=3RIhjKihu4Z1rruMt9KESFE2lqesfzIpRr7rLummUEo,10219
+pelican_nlp/Nils_backup/fluency/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pelican_nlp/Nils_backup/fluency/aggregate_fluency_results.py,sha256=VVsKR8_Epck-jk-uT6zNV-QO7EiM342MUzzHmVhOSdo,6392
+pelican_nlp/Nils_backup/fluency/behavioral_data.py,sha256=TJRpBhOh9JMdoL6OcNwhlChe_sNTFQlAhVKl2ml0X0w,1181
+pelican_nlp/Nils_backup/fluency/check_duplicates.py,sha256=XjfF7NEkilNmPdU0yOVug7xqsc6JbRu-HYO54FZQ8hg,6126
+pelican_nlp/Nils_backup/fluency/coherence.py,sha256=JGv-3RWwwYboEDZep2mQMuNivZNjV_H5ZrjwY2JHS10,21437
+pelican_nlp/Nils_backup/fluency/config.py,sha256=Ef9NdLcpCe6XH690plV5FBM_KEjoZR0wy9uYCdAFo78,9233
+pelican_nlp/Nils_backup/fluency/main.py,sha256=zMDTeNRj971xlMGSb7UOz-l0uvXG3kEeX4U06R_Vbv8,5910
+pelican_nlp/Nils_backup/fluency/optimality_without_tsa.py,sha256=ZmuQY25n7nVClYjF7j17M4kW0PbXzKCVvTVlDvZ_xa0,15065
+pelican_nlp/Nils_backup/fluency/plot_fluency.py,sha256=4SrnLhGPG0u-ycW9ryxEX02o3qasQiG_aMxMDpfNbcE,20749
+pelican_nlp/Nils_backup/fluency/plotting_utils.py,sha256=d0G9qSfBfrfnUCAvM_Su8xOH0lLGwq5KmLBC5sUbx0g,4946
+pelican_nlp/Nils_backup/fluency/questionnaires_data.py,sha256=xKACAI078si__TiOGahiAvo0nz_UCiJrTV1oEsWPU8A,1175
+pelican_nlp/Nils_backup/fluency/stats_fluency.py,sha256=HXGMzSGjXJAmw_MnHU5wM16nWSgPkZCWCSYtKaSChPQ,42981
+pelican_nlp/Nils_backup/fluency/utils.py,sha256=yF7TS_HhUscb6ZgNnk61WJ4qBJLHAJUCt53UWwfIc0U,1340
+pelican_nlp/Nils_backup/transcription/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pelican_nlp/Nils_backup/transcription/annotation_tool.py,sha256=O528LXdvs4TkzD201szzHOrTBCZsJa51gr-6iRddGmg,40185
+pelican_nlp/Nils_backup/transcription/annotation_tool_boundaries.py,sha256=4NnGMWuORKqNp0YFnkD90BuyaPRpo64W2kKCboE9oFE,45384
+pelican_nlp/Nils_backup/transcription/annotation_tool_sandbox.py,sha256=UHyKmUtVTeBgdBCDVCntqJW9gQN2p2GgKIng6E0LKiw,40405
+pelican_nlp/Nils_backup/transcription/test.json,sha256=T1PNoYwrqgwDVLtfmj7L5e0Sq02OEbqHPC8RFhICuUU,2
+pelican_nlp/Nils_backup/transcription/transcribe_audio.py,sha256=uJUXtE6uTXg34FB3f_WQ4WeuikPcPJdlpVrw2Rf0P7M,12600
+pelican_nlp/Nils_backup/transcription/transcribe_audio_chunked.py,sha256=PZUJ9Cnu96Chhi-MQmaoEd4ximdCAwAdReBzPrHPlZE,27644
+pelican_nlp/Nils_backup/transcription/transcription.py,sha256=aoIH8vsMh5rAJ1_j44gN6yBxcG-7AoGklVlMPSNnfKU,33031
+pelican_nlp/Nils_backup/transcription/transcription_gui.py,sha256=HtVEWZyU6_w-viUT4KCf55ZnQY0VxaII5zds1CUqlv8,38482
+pelican_nlp/Nils_backup/transcription/word_boundaries.py,sha256=n6erYFVgDWLkgMnSNxcTJvJV7Lh557EjWTtEgbwrZVo,6976
+pelican_nlp/Nils_backup/transcription/output/holmes_control_nova_all_outputs.json,sha256=Eo2pseyXGWSRLs44fDBIAUU7d57gXFXcq4A58iuLoVo,212326
+pelican_nlp/Silvia_files/Opensmile/opensmile_feature_extraction.py,sha256=sJsthRqJI8bfH38H-OwyQdxXCBIrXEdFm3qSARamYIw,2093
+pelican_nlp/Silvia_files/prosogram/prosogram.py,sha256=ndjtTSgVzEchPEcRNb9jAHuiKRJYXI2C3Y__Deyc1rU,3324
+pelican_nlp/configuration_files/config_audio.yml,sha256=aUneGp32RkBQD2xxgYw7J4djWatfWEjTm7Z8UeO49ec,3868
+pelican_nlp/configuration_files/config_discourse.yml,sha256=WrZk5J2xWMQQPOu25BsqIOM5CrYcAhxCxoMcQVKbDIU,3661
+pelican_nlp/configuration_files/config_fluency.yml,sha256=nBTGJXnbj8IhWsJGwP4ZutZCeIu2ybHUepG7RAWA1y0,3060
+pelican_nlp/configuration_files/config_general.yml,sha256=dOBiqOhw0VgV0LZ1boYJhhjCsnTaYBk6qoCTai-fk-o,3474
+pelican_nlp/configuration_files/config_morteza.yml,sha256=T378fxvBY9hERVGsnXroDFCy8Zh5PIq4dyer2b5AiDY,3376
+pelican_nlp/core/__init__.py,sha256=whJc5dWsGsKn2IAw-D4BvCvUKW1sVtWYE1WJIuUr5uI,165
+pelican_nlp/core/audio_document.py,sha256=hhSJNgeqSYa6_uws2ho66agHhAdHuKN3EIEdIsIcXKg,586
+pelican_nlp/core/corpus.py,sha256=6pDRmeO0XoHylhjLE4Fi5Tc3HCMQJ-Xk0YRzEfz5Z1Y,15168
+pelican_nlp/core/document.py,sha256=j2HP5FX6cfmXHo7OWVFCX6cMsDyqsOmNlnGNNNfCm2c,8467
+pelican_nlp/core/subject.py,sha256=-pi3jDzb2zLiG8JNAi9i-9Jd-VtsPxDO4ShQci2QSMg,1059
+pelican_nlp/extraction/__init__.py,sha256=hfqFiaKpQBS6cwRm9Yd7MpOcV60_xJmwuQ2Kegary5k,84
+pelican_nlp/extraction/acoustic_feature_extraction.py,sha256=6Csrr6uotarhuAzxYlGFAil9K4PLUqa9vWw607peRoA,2319
+pelican_nlp/extraction/distance_from_randomness.py,sha256=yikZ3GK2dqpzuNFPVsjuUK0lo6kHOIoIhKPaVrGXRMQ,3365
+pelican_nlp/extraction/extract_embeddings.py,sha256=e5bcNlskd7f-JkWtfd7YutGV5bqcURKrAkETRyTx93Q,2457
+pelican_nlp/extraction/extract_logits.py,sha256=Lc7Es86T8mlSvLMhiDHpFdCc0kCZ9fNr3-VFnOyeybs,3869
+pelican_nlp/extraction/language_model.py,sha256=4tHJZIRCEeHVTwEf2jmOtu-zDGkdXiDjKmlpuxDuLiw,2929
+pelican_nlp/extraction/semantic_similarity.py,sha256=QhY5CAOAorxEo3UBWPlMegFvbySF0KH6j4j3m2I3_NY,2552
+pelican_nlp/extraction/test_documents/test_features.csv,sha256=LR_3m4vIm-YWKw5gI5ziswhS-NF9VhKv14c2udLxtJU,488482
+pelican_nlp/extraction/test_documents/wallace_1.15_3.txt,sha256=ShXxOHUZzGPNUqIcOn6-OYkarzNtTC22V05a_Xpvtlw,3731
+pelican_nlp/extraction/test_documents/wallace_1.1_3.txt,sha256=gs5REE10myK3Nm9JBOV8hjqKcMRkrl7BasuK7HSBe5M,3695
+pelican_nlp/extraction/test_documents/wallace_1_4.txt,sha256=95Z7gS92KERCocrbOAFbJntf5QoE-6p0GL67XQEffqI,3963
+pelican_nlp/metrics_statistics/embeddings_metrics_statistics.py,sha256=svXXyLEA62mLa0KUfSiOSFFMjYk17K7BJbxUoLf0l9w,1468
+pelican_nlp/praat/__init__.py,sha256=uSEaUZ2nw7lH0twbRJL5BltJTJpopj5XCVhIbeM42bg,1035
+pelican_nlp/preprocessing/LPDS.py,sha256=4UWkMMSrdU-nWVi8eKiWQSGD7f7lemB42aI0fFn6ZLU,4097
+pelican_nlp/preprocessing/__init__.py,sha256=ZYgOUlKPXmltYez3urPZmsAWRWSEqZ3_l_gN2aqd15s,293
+pelican_nlp/preprocessing/pipeline.py,sha256=t2zJAvZRO12MdAKQgm8XZxfZND7_8gFtzHF9Rq2L2aE,1796
+pelican_nlp/preprocessing/speaker_diarization.py,sha256=N6dZCa2AHHGw__g9e-ZUyZM_In0-nzFOkZ44cBnoKLk,1122
+pelican_nlp/preprocessing/text_cleaner.py,sha256=QKqxwoRR8dnuBYiY-PXK1kB7744TVUcUMJb7dbKvXGk,7512
+pelican_nlp/preprocessing/text_importer.py,sha256=FtSyJjFXDxVle7Jpyw6EqCLDbLTCRxqVQi9ymWWtPB4,1356
+pelican_nlp/preprocessing/text_normalizer.py,sha256=huo5VFqJ0p2jq-ud1047XvMu1qNeaiuG879SF3zkJoM,894
+pelican_nlp/preprocessing/text_tokenizer.py,sha256=h875bXr0YuMrLh4HtQUvpHmASScddtkQXGaF9mm7uwU,1642
+pelican_nlp/sample_configuration_files/config_discourse.yml,sha256=xVHIUpSORV6iR0nEvuess6rfiAvuGEkqmaMWD_6kyFE,3618
+pelican_nlp/sample_configuration_files/config_fluency.yml,sha256=oQ6Y2BhRLExEMpS3VRH2pFrGHi788L66aSYUm05nV_A,3038
+pelican_nlp/sample_configuration_files/config_general.yml,sha256=UuGnZUa-SVmioE9NmXWOMKuv3uG5mNjIuXgA6-Y0JS0,3440
+pelican_nlp/utils/__init__.py,sha256=q1tGdOOj5UPRC2mGhoMUh8p4cbFCkkbD21bQaOVvFao,189
+pelican_nlp/utils/csv_functions.py,sha256=hsG73gm3Up9sAerp6gIxuNHaeP1vJj6HSh7ggVm1SSo,7272
+pelican_nlp/utils/sample_usage.py,sha256=W__OVMjWND-ZtxxRhfGJDHwbVpGlB-anXDxyA5P4cME,353
+pelican_nlp/utils/setup_functions.py,sha256=s0QcarswU8qeFBcEQNIYC1ooaD-xwRiTJn--yPEId8E,3612
+pelican_nlp-0.1.2.dist-info/licenses/LICENSE,sha256=m3jshBZIXKiBX6qhmhtJcLTVJ1N6BEkQGIflneXvpYg,19336
+pelican_nlp-0.1.2.dist-info/METADATA,sha256=Iuz8Y4HbCCFdcCYvXlGjANQBGd9Zf1Ez6tjD9nnVLuw,5001
+pelican_nlp-0.1.2.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+pelican_nlp-0.1.2.dist-info/top_level.txt,sha256=F0qlyqy5FCd3sTS_npUYPeLKN9_BZq6wD4qo9pI0xbg,12
+pelican_nlp-0.1.2.dist-info/RECORD,,

pelican_nlp-0.1.1.dist-info/RECORD

@@ -1,39 +0,0 @@
-pelican_nlp/__init__.py,sha256=opumkxDDKxGZgYyNkkUiu8kbOrBixP8zP_bhljYYktc,192
-pelican_nlp/main.py,sha256=xKUqqA3sh9kbk07lKA_poILIU1c8oIeaSsVqPOPY5Tk,7596
-pelican_nlp/core/__init__.py,sha256=whJc5dWsGsKn2IAw-D4BvCvUKW1sVtWYE1WJIuUr5uI,165
-pelican_nlp/core/audio_document.py,sha256=hhSJNgeqSYa6_uws2ho66agHhAdHuKN3EIEdIsIcXKg,586
-pelican_nlp/core/corpus.py,sha256=6pDRmeO0XoHylhjLE4Fi5Tc3HCMQJ-Xk0YRzEfz5Z1Y,15168
-pelican_nlp/core/document.py,sha256=j2HP5FX6cfmXHo7OWVFCX6cMsDyqsOmNlnGNNNfCm2c,8467
-pelican_nlp/core/subject.py,sha256=-pi3jDzb2zLiG8JNAi9i-9Jd-VtsPxDO4ShQci2QSMg,1059
-pelican_nlp/extraction/__init__.py,sha256=hfqFiaKpQBS6cwRm9Yd7MpOcV60_xJmwuQ2Kegary5k,84
-pelican_nlp/extraction/acoustic_feature_extraction.py,sha256=6Csrr6uotarhuAzxYlGFAil9K4PLUqa9vWw607peRoA,2319
-pelican_nlp/extraction/distance_from_randomness.py,sha256=yikZ3GK2dqpzuNFPVsjuUK0lo6kHOIoIhKPaVrGXRMQ,3365
-pelican_nlp/extraction/extract_embeddings.py,sha256=e5bcNlskd7f-JkWtfd7YutGV5bqcURKrAkETRyTx93Q,2457
-pelican_nlp/extraction/extract_logits.py,sha256=Lc7Es86T8mlSvLMhiDHpFdCc0kCZ9fNr3-VFnOyeybs,3869
-pelican_nlp/extraction/language_model.py,sha256=4tHJZIRCEeHVTwEf2jmOtu-zDGkdXiDjKmlpuxDuLiw,2929
-pelican_nlp/extraction/semantic_similarity.py,sha256=QhY5CAOAorxEo3UBWPlMegFvbySF0KH6j4j3m2I3_NY,2552
-pelican_nlp/extraction/test_documents/test_features.csv,sha256=LR_3m4vIm-YWKw5gI5ziswhS-NF9VhKv14c2udLxtJU,488482
-pelican_nlp/extraction/test_documents/wallace_1.15_3.txt,sha256=ShXxOHUZzGPNUqIcOn6-OYkarzNtTC22V05a_Xpvtlw,3731
-pelican_nlp/extraction/test_documents/wallace_1.1_3.txt,sha256=gs5REE10myK3Nm9JBOV8hjqKcMRkrl7BasuK7HSBe5M,3695
-pelican_nlp/extraction/test_documents/wallace_1_4.txt,sha256=95Z7gS92KERCocrbOAFbJntf5QoE-6p0GL67XQEffqI,3963
-pelican_nlp/metrics_statistics/embeddings_metrics_statistics.py,sha256=svXXyLEA62mLa0KUfSiOSFFMjYk17K7BJbxUoLf0l9w,1468
-pelican_nlp/preprocessing/LPDS.py,sha256=4UWkMMSrdU-nWVi8eKiWQSGD7f7lemB42aI0fFn6ZLU,4097
-pelican_nlp/preprocessing/__init__.py,sha256=ZYgOUlKPXmltYez3urPZmsAWRWSEqZ3_l_gN2aqd15s,293
-pelican_nlp/preprocessing/pipeline.py,sha256=t2zJAvZRO12MdAKQgm8XZxfZND7_8gFtzHF9Rq2L2aE,1796
-pelican_nlp/preprocessing/speaker_diarization.py,sha256=N6dZCa2AHHGw__g9e-ZUyZM_In0-nzFOkZ44cBnoKLk,1122
-pelican_nlp/preprocessing/text_cleaner.py,sha256=QKqxwoRR8dnuBYiY-PXK1kB7744TVUcUMJb7dbKvXGk,7512
-pelican_nlp/preprocessing/text_importer.py,sha256=FtSyJjFXDxVle7Jpyw6EqCLDbLTCRxqVQi9ymWWtPB4,1356
-pelican_nlp/preprocessing/text_normalizer.py,sha256=huo5VFqJ0p2jq-ud1047XvMu1qNeaiuG879SF3zkJoM,894
-pelican_nlp/preprocessing/text_tokenizer.py,sha256=h875bXr0YuMrLh4HtQUvpHmASScddtkQXGaF9mm7uwU,1642
-pelican_nlp/sample_configuration_files/config_discourse.yml,sha256=xVHIUpSORV6iR0nEvuess6rfiAvuGEkqmaMWD_6kyFE,3618
-pelican_nlp/sample_configuration_files/config_fluency.yml,sha256=oQ6Y2BhRLExEMpS3VRH2pFrGHi788L66aSYUm05nV_A,3038
-pelican_nlp/sample_configuration_files/config_general.yml,sha256=UuGnZUa-SVmioE9NmXWOMKuv3uG5mNjIuXgA6-Y0JS0,3440
-pelican_nlp/utils/__init__.py,sha256=q1tGdOOj5UPRC2mGhoMUh8p4cbFCkkbD21bQaOVvFao,189
-pelican_nlp/utils/csv_functions.py,sha256=hsG73gm3Up9sAerp6gIxuNHaeP1vJj6HSh7ggVm1SSo,7272
-pelican_nlp/utils/sample_usage.py,sha256=W__OVMjWND-ZtxxRhfGJDHwbVpGlB-anXDxyA5P4cME,353
-pelican_nlp/utils/setup_functions.py,sha256=s0QcarswU8qeFBcEQNIYC1ooaD-xwRiTJn--yPEId8E,3612
-pelican_nlp-0.1.1.dist-info/licenses/LICENSE,sha256=m3jshBZIXKiBX6qhmhtJcLTVJ1N6BEkQGIflneXvpYg,19336
-pelican_nlp-0.1.1.dist-info/METADATA,sha256=WV78gC4295adtWepMzCQm1yCkUa1LIBm9vkz9YFx3Dk,4986
-pelican_nlp-0.1.1.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-pelican_nlp-0.1.1.dist-info/top_level.txt,sha256=F0qlyqy5FCd3sTS_npUYPeLKN9_BZq6wD4qo9pI0xbg,12
-pelican_nlp-0.1.1.dist-info/RECORD,,