Small changes to gitignore and README

Author: griko

.gitignore

@@ -25,6 +25,7 @@
 /src/notebook_examples/pretrained_models/**
 /src/notebook_examples/wav2vec2_checkpoints/**
 
+.vscode/
 
 
 ### JetBrains template

README.md

@@ -1,24 +1,24 @@
-# vanpy 
-**vanpy** is a Voice Analysis framework, built in a 
+# VANPY 
+**VANPY** is a Voice Analysis framework, built in a 
 flexible manner for easy extendability, that allows to extract and classify voice segments. 
 
-![vanpy](https://user-images.githubusercontent.com/1709151/176196445-d80903ec-295f-4bc2-8a82-7f25f9f8dfc1.PNG)
+![VANPY](https://user-images.githubusercontent.com/1709151/176196445-d80903ec-295f-4bc2-8a82-7f25f9f8dfc1.PNG)
 
 ## Examples
 You can use the following google colab notebook to inspect the capabilities of the library
 
-[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/griko/vanpy/blob/main/examples/vanpy_example.ipynb)
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/griko/VANPY/blob/main/examples/VANPY_example.ipynb)
 
-Voice emotion classification model training and evaluation on RAVDESS dataset using **vanpy**
+Voice emotion classification model training and evaluation on RAVDESS dataset using **VANPY**
 
-[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/griko/vanpy/blob/main/examples/using_vanpy_to_classify_emotions_on_RAVDESS_dataset.ipynb)
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/griko/VANPY/blob/main/examples/using_VANPY_to_classify_emotions_on_RAVDESS_dataset.ipynb)
 
 Expending the library with a new classifier
 
 *TODO*
 
 ## Description
-**vanpy** can be useful in multiple ways. It contains of 3 optional pipelines, that make preprocessing, feature 
+**VANPY** can be useful in multiple ways. It contains of 3 optional pipelines, that make preprocessing, feature 
 extraction and classification/STT of a voice segments an easy task:
 
 1. The preprocessing pipline deals with audio files format and voice segment cutting. 

src/run.py

@@ -72,8 +72,11 @@ def main():
 
 
     # pipeline = Pipeline(['file_mapper', 'pyannote_sd', 'speechbrain_embedding', 'openai_whisper_stt'], config=config)
-    pipeline = Pipeline(['file_mapper', 'pyannote_sd', 'librosa_features_extractor', 'speechbrain_embedding', 'vanpy_gender', 'vanpy_age', 'vanpy_height', 'vanpy_emotion'], config=config)
-
+    # pipeline = Pipeline(['file_mapper', 'pyannote_sd', 'librosa_features_extractor', 'speechbrain_embedding', 'vanpy_gender', 'vanpy_age', 'vanpy_height', 'vanpy_emotion'], config=config)
+    pipeline = Pipeline(['file_mapper', 'pyannote_vad', 'speechbrain_embedding', 'openai_whisper_stt', 'speech_brain_iemocap_emotion',
+                         'wav2vec2adv', 'yamnet_classifier', 'cosine_distance_diarization', 'agglomerative_clustering_diarization', 'gmm_clustering_diarization'], config=config)
+    pipeline = Pipeline(['file_mapper', 'metricgan_se', 'ina_speech_segmenter', 'sepformer_se', 'wav2vec2stt',
+                         'wav2vec2adv', 'yamnet_classifier'], config=config)
 
     # pipeline = Pipeline(['file_mapper', 'speechbrain_embedding', 'vanpy_ravdess_emotion'], config=config)
     # 'wav_converter', 'metricgan_se',, 'silero_vad', 'speechbrain_embedding', 'cosine_distance_diarization' , 'pyannote_sd', 'openai_whisper_stt'