Update download_models.py

download_models.py

@@ -1,19 +1,110 @@
 import os
 from transformers import Wav2Vec2ForCTC, Wav2Vec2Tokenizer
+import nltk
+import os
+
+# Define the directory to save the data
+data_dir = 'nltk_data'
+
+# Create the directory if it does not exist
+if not os.path.exists(data_dir):
+    os.makedirs(data_dir)
+
+# Set the NLTK data path to the local directory
+nltk.data.path.append(data_dir)
+
+# Download the required NLTK data
+nltk.download('punkt', download_dir=data_dir)
+nltk.download('words', download_dir=data_dir)
+
+
+
+
+
+from transformers import Wav2Vec2Tokenizer, Wav2Vec2ForCTC, DistilBertTokenizer, DistilBertForSequenceClassification
+import os
+
+# Define directories to save the models and tokenizers
+pronunciation_model_dir = 'pronunciation_model'
+fluency_model_dir = 'fluency_model'
+
+# Create the directories if they don't exist
+os.makedirs(pronunciation_model_dir, exist_ok=True)
+os.makedirs(fluency_model_dir, exist_ok=True)
+
+# Download and save the Pronunciation model and tokenizer
+print("Downloading pronunciation tokenizer...")
+pronunciation_tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
+pronunciation_tokenizer.save_pretrained(pronunciation_model_dir)
+
+print("Downloading pronunciation model...")
+pronunciation_model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
+pronunciation_model.save_pretrained(pronunciation_model_dir)
+
+# Download and save the Fluency model and tokenizer
+print("Downloading fluency tokenizer...")
+fluency_tokenizer = DistilBertTokenizer.from_pretrained('distilbert-base-uncased')
+fluency_tokenizer.save_pretrained(fluency_model_dir)
+
+print("Downloading fluency model...")
+fluency_model = DistilBertForSequenceClassification.from_pretrained("Kartikeyssj2/Fluency_Scoring_V2")
+fluency_model.save_pretrained(fluency_model_dir)
+
+print("Download and save completed.")
+
+
+
+
+
+
+
+from sentence_transformers import SentenceTransformer
+import os
+
+# Define the directory to save the model
+model_dir = 'content_relevance_model'
+
+# Create the directory if it does not exist
+os.makedirs(model_dir, exist_ok=True)
+
+# Download and save the SentenceTransformer model
+print("Downloading SentenceTransformer model...")
+model = SentenceTransformer('sentence-transformers/msmarco-distilbert-cos-v5')
+model.save(model_dir)
+
+print("Model downloaded and saved successfully.")
+
+
+
+
+
+
+from transformers import BlipProcessor, BlipForConditionalGeneration
+import os
+
+# Define directories to save the models and processors
+processor_dir = 'blip_processor'
+model_dir = 'blip_model'
+
+# Create the directories if they don't exist
+os.makedirs(processor_dir, exist_ok=True)
+os.makedirs(model_dir, exist_ok=True)
+
+# Download and save the BlipProcessor
+print("Downloading BlipProcessor...")
+image_captioning_processor = BlipProcessor.from_pretrained("noamrot/FuseCap")
+image_captioning_processor.save_pretrained(processor_dir)
+print("BlipProcessor downloaded and saved.")
+
+# Download and save the BlipForConditionalGeneration model
+print("Downloading BlipForConditionalGeneration model...")
+image_captioning_model = BlipForConditionalGeneration.from_pretrained("noamrot/FuseCap")
+image_captioning_model.save_pretrained(model_dir)
+print("BlipForConditionalGeneration model downloaded and saved.")
+
+
+
 
-# Create the models directory if it doesn't exist
-os.makedirs("./models", exist_ok=True)
-os.makedirs("./models/tokenizer", exist_ok=True)
-os.makedirs("./models/model", exist_ok=True)
 
-print("Downloading and saving tokenizer...")
-tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-base-960h")
-tokenizer.save_pretrained("./models/tokenizer")
-print("Tokenizer saved successfully.")
 
-print("Downloading and saving model...")
-model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
-model.save_pretrained("./models/model")
-print("Model saved successfully.")
 
-print("Download and save process completed.")