Spaces:
Build error
Build error
File size: 3,011 Bytes
55137ed b9da6aa 55137ed 2c8b5b1 b9da6aa 55137ed b9da6aa 55137ed b9da6aa 2c8b5b1 55137ed b9da6aa 55137ed b9da6aa 55137ed b9da6aa 2c8b5b1 b9da6aa 55137ed b9da6aa 55137ed b9da6aa 55137ed 2c8b5b1 fce3faa 2c8b5b1 55137ed 0d82e75 |
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 |
import streamlit as st
from transformers import AutoModelForCausalLM, AutoTokenizer
from gtts import gTTS
import tempfile
import os
import speech_recognition as sr
# Set your Hugging Face API key
HUGGING_FACE_API_KEY = "voicebot"
# Load the model and tokenizer
@st.cache_resource
def load_model():
model_name = "declare-lab/tango-full"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=HUGGING_FACE_API_KEY)
return model, tokenizer
model, tokenizer = load_model()
# Function to get a response from the chatbot
def get_response(input_text):
inputs = tokenizer.encode(input_text, return_tensors='pt')
response_ids = model.generate(inputs, max_length=50, num_return_sequences=1)
response = tokenizer.decode(response_ids[0], skip_special_tokens=True)
return response
# Function to convert text to speech
def text_to_speech(text):
tts = gTTS(text=text, lang='en')
with tempfile.NamedTemporaryFile(delete=True) as fp:
tts.save(f"{fp.name}.mp3")
os.system(f"start {fp.name}.mp3") # Adjust command based on OS
# Speech Recognition Function
def recognize_speech():
r = sr.Recognizer()
with sr.Microphone() as source:
st.write("Listening...")
audio = r.listen(source)
st.write("Recognizing...")
try:
text = r.recognize_google(audio)
st.success(f"You said: {text}")
return text
except sr.UnknownValueError:
st.error("Sorry, I could not understand the audio.")
return None
except sr.RequestError:
st.error("Could not request results from Google Speech Recognition service.")
return None
# Streamlit Interface
st.title("Voice-to-Text Chatbot")
# Recognize speech
if st.button("Speak"):
user_input = recognize_speech()
else:
user_input = st.text_input("Type your message here:")
# Display response and convert to speech
if user_input:
st.write("You: ", user_input)
chatbot_response = get_response(user_input)
st.write("Chatbot: ", chatbot_response)
text_to_speech(chatbot_response)
text_to_speech(chatbot_response)
import logging
# Configure logging
logging.basicConfig(level=logging.INFO)
# Use logging instead of print for more structured output
def load_model():
try:
logging.info("Loading model...")
model_name = "declare-lab/tango-full"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=HUGGING_FACE_API_KEY)
logging.info("Model loaded successfully.")
return model, tokenizer
except Exception as e:
logging.error(f"Error loading model: {e}")
raise
# Example usage in your Streamlit code
if __name__ == "__main__":
try:
model, tokenizer = load_model()
except Exception as e:
logging.error(f"Application failed to start: {e}")
|