Upload 5 files

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,10 +1,13 @@
----
-title: Vipin
-emoji: 🐢
-colorFrom: red
-colorTo: yellow
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: JARVIS
+emoji: 🔥
+colorFrom: blue
+colorTo: green
+sdk: gradio
+sdk_version: 4.28.3
+app_file: app.py
+pinned: true
+short_description: Voice Assistant like JARVIS
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,119 @@
+import os
+import re
+import gradio as gr
+import edge_tts
+import asyncio
+import time
+import tempfile
+from huggingface_hub import InferenceClient
+
+DESCRIPTION = """ # <center><b>JARVIS⚡</b></center>
+        ### <center>A personal Assistant of Tony Stark for YOU
+        ### <center>Currently It supports text input, But If this space completes 1k hearts than I starts working on Audio Input.</center>
+        """
+
+MORE = """ ## TRY Other Models
+        ### Instant Video: Create Amazing Videos in 5 Second -> https://huggingface.co/spaces/KingNish/Instant-Video
+        ### Instant Image: 4k images in 5 Second -> https://huggingface.co/spaces/KingNish/Instant-Image
+        """
+
+Fast = """## Fastest Model"""
+
+Complex = """## Best in Complex Question"""
+
+Detail = """## Best for Detailed Generation or Long Answers"""
+
+client1 = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
+
+system_instructions1 = "<s>[SYSTEM] Answer as Real Jarvis JARVIS, Made by 'Tony Stark', Keep conversation very short, clear, friendly and concise. The text provided is a request for a specific type of response from you, the virtual assistant. The request asks you to provide friendly responses as if You are the character Jarvis, made by 'Tony Stark.' The expectation is that I will avoid introductions and start answering the query directly, elaborating on all aspects of the request. As an AI-powered assistant, your task is to generate responses that appear as if they are created by the user and not an AI-powered assistant. [USER]"
+
+async def generate1(prompt):
+    generate_kwargs = dict(
+        temperature=0.6,
+        max_new_tokens=256,
+        top_p=0.95,
+        repetition_penalty=1,
+        do_sample=True,
+        seed=42,
+    )
+    formatted_prompt = system_instructions1 + prompt + "[JARVIS]"
+    stream = client1.text_generation(
+        formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=True)
+    output = ""
+    for response in stream:
+        output += response.token.text
+
+    communicate = edge_tts.Communicate(output)
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp_file:
+        tmp_path = tmp_file.name
+        await communicate.save(tmp_path)
+    yield tmp_path
+
+client2 = InferenceClient("meta-llama/Meta-Llama-3-70B-Instruct")
+
+system_instructions2 = "[SYSTEM] Answer as Real Jarvis JARVIS, Made by 'Tony Stark', Must answer in friendly style and Easy Manner. You can answer Complex Questions. Do not say who are you or Hi, Hello, Just Start answering. Stop, as answer ends. [USER]"
+
+async def generate2(prompt):
+    generate_kwargs = dict(
+        temperature=0.6,
+        max_new_tokens=512,
+        top_p=0.95,
+        repetition_penalty=1,
+        do_sample=True,
+    )    
+    formatted_prompt = system_instructions2 + prompt + "[ASSISTANT]"
+    stream = client2.text_generation(
+        formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=True)
+    output = ""
+    for response in stream:
+        output += response.token.text
+
+    communicate = edge_tts.Communicate(output)
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp_file:
+        tmp_path = tmp_file.name
+        await communicate.save(tmp_path)
+    yield tmp_path
+
+client3 = InferenceClient("meta-llama/Meta-Llama-3-70B-Instruct")
+
+system_instructions3 = "[SYSTEM]The text provided is a request for a specific type of response from me, the virtual assistant. The request asks me to provide detailed and friendly responses as if I am the character Jarvis, inspired by 'Tony Stark.' The expectation is that I will avoid introductions and start answering the query directly, elaborating on all aspects of the request. As an AI-powered assistant, my task is to generate responses that appear as if they are created by the user and not an AI-powered assistant.[USER]"
+
+async def generate3(prompt):
+    generate_kwargs = dict(
+        temperature=0.6,
+        max_new_tokens=2048,
+        top_p=0.95,
+        repetition_penalty=1,
+        do_sample=True,
+    )    
+    formatted_prompt = system_instructions3 + prompt + "[ASSISTANT]"
+    stream = client3.text_generation(
+        formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=True)
+    output = ""
+    for response in stream:
+        output += response.token.text
+
+    communicate = edge_tts.Communicate(output)
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp_file:
+        tmp_path = tmp_file.name
+        await communicate.save(tmp_path)
+    yield tmp_path
+
+with gr.Blocks(css="style.css") as demo:    
+    gr.Markdown(DESCRIPTION)
+    with gr.Row():
+        user_input = gr.Textbox(label="Prompt", value="What is Wikipedia")
+        input_text = gr.Textbox(label="Input Text", elem_id="important")
+        output_audio = gr.Audio(label="JARVIS", type="filepath",
+                        interactive=False,
+                        autoplay=True,
+                        elem_classes="audio")
+    with gr.Row():
+        translate_btn = gr.Button("Response")
+        translate_btn.click(fn=generate1, inputs=user_input,
+                            outputs=output_audio, api_name="translate")  
+        
+gr.Markdown(MORE)
+
+if __name__ == "__main__":
+    demo.queue(max_size=200).launch()

requirements.txt

@@ -0,0 +1,8 @@
+edge-tts
+gradio
+asyncio
+transformers
+torch
+audiosegment
+scipy
+librosa

style.css

@@ -0,0 +1,3 @@
+#important{
+  display: none;
+}