File size: 4,366 Bytes
59e3a51 b3bbe1c 63a3a84 e63873f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 |
from huggingfaceinferenceclient import HuggingFaceInferenceClient
from outpaintprocessor import DynamicImageOutpainter
from aivideopipeline import AIImageVideoPipeline
from mmig import MultiModelImageGenerator
import os
import requests
from PIL import Image
from io import BytesIO
from huggingface_hub import InferenceClient
from IPython.display import Audio, display
import gradio as gr
# Whisper for Speech-to-Text
WHISPER_API_URL = "https://api-inference.huggingface.co/models/distil-whisper/distil-large-v2"
WHISPER_HEADERS = {"Authorization": "Bearer hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"}
def speech_to_text(filename):
with open(filename, "rb") as f:
data = f.read()
response = requests.post(WHISPER_API_URL, headers=WHISPER_HEADERS, data=data)
if response.status_code == 200:
return response.json().get("text", "Could not recognize speech")
else:
print(f"Error: {response.status_code} - {response.text}")
return None
# Chatbot Logic with Hugging Face InferenceClient
client = InferenceClient(api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx")
def chatbot_logic(input_text):
messages = [{"role": "user", "content": input_text}]
try:
completion = client.chat.completions.create(
model="mistralai/Mistral-Nemo-Instruct-2407",
messages=messages,
max_tokens=500
)
return completion.choices[0].message["content"]
except Exception as e:
print(f"Error: {e}")
return None
# Bark for Text-to-Speech
BARK_API_URL = "https://api-inference.huggingface.co/models/suno/bark"
BARK_HEADERS = {"Authorization": "Bearer hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"}
def text_to_speech(text):
payload = {"inputs": text}
response = requests.post(BARK_API_URL, headers=BARK_HEADERS, json=payload)
if response.status_code == 200:
return response.content
else:
print(f"Error: {response.status_code} - {response.text}")
return None
# Flux for Image Generation
FLUX_API_URL = "https://api-inference.huggingface.co/models/enhanceaiteam/Flux-uncensored"
FLUX_HEADERS = {"Authorization": "Bearer hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"}
def generate_image(prompt):
data = {"inputs": prompt}
response = requests.post(FLUX_API_URL, headers=FLUX_HEADERS, json=data)
if response.status_code == 200:
image_bytes = BytesIO(response.content)
return Image.open(image_bytes)
else:
print(f"Error: {response.status_code} - {response.text}")
return None
# Gradio Interface for Chatbot and Image Generator
def create_ui():
def process_chat(audio_file):
# Step 1: Speech to Text
recognized_text = speech_to_text(audio_file)
if not recognized_text:
return "Could not recognize speech", None, None
# Step 2: Chatbot Logic
response_text = chatbot_logic(recognized_text)
if not response_text:
return f"Error generating response for: {recognized_text}", None, None
# Step 3: Text to Speech
audio_output = text_to_speech(response_text)
if not audio_output:
return f"Error synthesizing response: {response_text}", None, None
# Step 4: Image Generation
generated_image = generate_image(response_text)
return response_text, Audio(audio_output, autoplay=True), generated_image
with gr.Blocks(title="Voice-to-Voice Chatbot with Image Generation") as ui:
gr.Markdown("## Voice-to-Voice Chatbot with Image Generation\nUpload an audio file to interact with the chatbot.")
audio_input = gr.Audio(source="upload", type="filepath", label="Input Audio File")
submit_button = gr.Button("Process")
with gr.Row():
chatbot_response = gr.Textbox(label="Chatbot Response", lines=2)
with gr.Row():
audio_output = gr.Audio(label="Generated Audio Response")
image_output = gr.Image(label="Generated Image")
submit_button.click(
fn=process_chat,
inputs=audio_input,
outputs=[chatbot_response, audio_output, image_output],
show_progress=True
)
return ui
# Run the Gradio Interface
if __name__ == "__main__":
create_ui().launch(debug=True)
|