Upload 3 files

app.py

@@ -0,0 +1,57 @@
+import gradio as gr
+from transformers import pipeline
+from models.jairvis import JAIRVISMKV
+from utils.audio_utils import text_to_speech, speech_to_text
+from utils.memory_manager import MemoryManager
+from config import MODEL_NAME, API_KEY
+
+class JairvisApp:
+    def __init__(self):
+        self.jairvis = JAIRVISMKV()
+        self.memory_manager = MemoryManager()
+        self.nlp_pipeline = pipeline("text-generation", model=MODEL_NAME)
+
+    def process_input(self, input_text):
+        # Process input and generate response
+        response = self.jairvis.generate_response(input_text)
+        
+        # Update memory
+        self.memory_manager.store(input_text, response)
+        
+        # Convert response to speech
+        audio_output = text_to_speech(response)
+        
+        return response, audio_output
+
+    def voice_input(self, audio):
+        # Convert speech to text
+        input_text = speech_to_text(audio)
+        
+        # Process the text input
+        response, audio_output = self.process_input(input_text)
+        
+        return input_text, response, audio_output
+
+# Set up the Gradio interface
+def launch():
+    app = JairvisApp()
+    
+    text_interface = gr.Interface(
+        fn=app.process_input,
+        inputs="text",
+        outputs=["text", "audio"],
+        title="JAIRVISMKV Text Interface"
+    )
+    
+    voice_interface = gr.Interface(
+        fn=app.voice_input,
+        inputs="audio",
+        outputs=["text", "text", "audio"],
+        title="JAIRVISMKV Voice Interface"
+    )
+    
+    combined_interface = gr.TabbedInterface([text_interface, voice_interface], ["Text", "Voice"])
+    combined_interface.launch()
+
+if __name__ == "__main__":
+    launch()

config.py

@@ -0,0 +1,19 @@
+import torch
+
+# Model configurations
+MODEL_NAME = "gpt2-medium"
+SPEECH_MODEL = "facebook/wav2vec2-base-960h"
+TTS_MODEL = "v3_en"
+
+# Device configuration
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Memory configurations
+MEMORY_SIZE = 10 * 1024 * 1024 * 1024  # 10GB in bytes
+LOCAL_MEMORY_SIZE = 3 * 1024 * 1024 * 1024  # 3GB in bytes
+
+# API configurations
+API_KEY = "your_huggingface_api_key_here"
+
+# Conversation settings
+MAX_CONTEXT_LENGTH = 3024

requirements.txt

@@ -0,0 +1,172 @@
+absl-py==2.1.0
+annotated-types==0.7.0
+anyio==4.4.0
+area==1.1.1
+astunparse==1.6.3
+attrs==24.2.0
+beautifulsoup4==4.12.3
+blis==0.7.11
+bs4==0.0.2
+cachetools==5.5.0
+catalogue==2.0.10
+certifi==2024.8.30
+cffi==1.17.1
+charset-normalizer==3.3.2
+click==8.1.7
+cloudpathlib==0.19.0
+colorama==0.4.6
+comtypes==1.4.7
+confection==0.1.5
+contourpy==1.3.0
+cryptography==43.0.1
+cycler==0.12.1
+cymem==2.0.8
+distro==1.9.0
+face-detection-tflite==0.6.0
+filelock==3.16.0
+fitbit==0.3.1
+flatbuffers==24.3.25
+fonttools==4.53.1
+fsspec==2024.9.0
+gast==0.6.0
+google-ai-generativelanguage==0.6.6
+google-api-core==2.19.2
+google-api-python-client==2.144.0
+google-auth==2.34.0
+google-auth-httplib2==0.2.0
+google-auth-oauthlib==1.2.1
+google-generativeai==0.7.2
+google-oauth==1.0.1
+google-pasta==0.2.0
+googleapis-common-protos==1.65.0
+GPUtil==1.4.0
+gputils==1.0.6
+grpcio==1.66.1
+grpcio-status==1.62.3
+h11==0.14.0
+h5py==3.11.0
+httpcore==1.0.5
+httplib2==0.22.0
+httpx==0.27.2
+huggingface-hub==0.24.6
+idna==3.8
+jax==0.4.31
+jaxlib==0.4.31
+Jinja2==3.1.4
+jiter==0.5.0
+joblib==1.4.2
+keras==3.5.0
+keras-facenet==0.3.2
+kiwisolver==1.4.7
+langcodes==3.4.0
+language_data==1.2.0
+libclang==18.1.1
+marisa-trie==1.2.0
+Markdown==3.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+mdurl==0.1.2
+mediapipe==0.10.14
+ml-dtypes==0.4.0
+MouseInfo==0.1.3
+mpmath==1.3.0
+mtcnn==0.1.1
+murmurhash==1.0.10
+namex==0.0.8
+networkx==3.3
+nltk==3.9.1
+numpy==1.26.4
+oauth2==1.9.0.post1
+oauthlib==3.2.2
+openai==1.44.1
+opencv-contrib-python==4.10.0.84
+opencv-python==4.10.0.84
+opt-einsum==3.3.0
+optree==0.12.1
+packaging==24.1
+pandas==2.2.2
+pillow==10.4.0
+preshed==3.0.9
+progressbar2==4.5.0
+proto-plus==1.24.0
+protobuf==4.25.4
+psutil==6.0.0
+pushbullet.py==0.12.0
+pyasn1==0.6.0
+pyasn1_modules==0.4.0
+PyAudio==0.2.14
+PyAutoGUI==0.9.54
+pycoral==0.2.0
+pycparser==2.22
+pycryptodome==3.20.0
+pydantic==2.9.1
+pydantic_core==2.23.3
+pyDes==2.0.1
+pydub==0.25.1
+PyGetWindow==0.0.9
+Pygments==2.18.0
+PyMsgBox==1.0.9
+pyOpenSSL==24.2.1
+pyparsing==3.1.4
+pyperclip==1.9.0
+pypiwin32==223
+PyRect==0.2.0
+PyScreeze==1.0.1
+python-dateutil==2.9.0.post0
+python-magic==0.4.27
+python-utils==3.8.2
+pyttsx3==2.91
+pytweening==1.2.0
+pytz==2024.1
+pywifi==1.1.12
+pywin32==306
+PyYAML==6.0.2
+regex==2024.7.24
+requests==2.32.3
+requests-oauthlib==2.0.0
+rich==13.8.0
+rsa==4.9
+safetensors==0.4.5
+scapy==2.5.0
+scikit-learn==1.5.1
+scipy==1.14.1
+shellingham==1.5.4
+six==1.16.0
+smart-open==7.0.4
+sniffio==1.3.1
+sounddevice==0.5.0
+soupsieve==2.6
+spacy==3.7.6
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+SpeechRecognition==3.10.4
+srsly==2.4.8
+sympy==1.13.2
+tenacity==9.0.0
+tensorboard==2.17.1
+tensorboard-data-server==0.7.2
+tensorflow==2.17.0
+tensorflow-intel==2.17.0
+termcolor==2.4.0
+textblob==0.18.0.post0
+tf_keras==2.17.0
+thinc==8.2.5
+threadpoolctl==3.5.0
+tokenizers==0.19.1
+torch==2.4.1
+tqdm==4.66.5
+transformers==4.44.2
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.1
+uritemplate==4.1.1
+urllib3==2.2.2
+wasabi==1.1.3
+weasel==0.4.1
+websocket-client==1.8.0
+Werkzeug==3.0.4
+wrapt==1.16.0
+gradio
+fastapi
+uvicorn