Create app.py

app.py

@@ -0,0 +1,131 @@
+import streamlit as st
+from deep_translator import GoogleTranslator
+from streamlit_mic_recorder import speech_to_text
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
+from sentence_transformers import SentenceTransformer, util
+import json
+import time
+st.set_page_config(layout="wide")
+# Language dictionaries
+language_dict = {
+    'English': 'en', 'Hindi': 'hi', 'Bengali': 'bn', 'Gujarati': 'gu', 'Marathi': 'mr',
+    'Telugu': 'te', 'Tamil': 'ta', 'Punjabi': 'pa', 'Odia': 'or', 'Nepali': 'ne', 'Malayalam': 'ml'
+}
+
+nllb_langs = {
+    'English':'eng_Latn','Hindi':'hin_Deva','Punjabi':'pan_Guru','Odia':'ory_Orya',
+    'Bengali':'ben_Beng','Telugu':'tel_Telu','Tamil':'tam_Taml','Nepali':'npi_Deva',
+    'Marathi':'mar_Deva','Malayalam':'mal_Mlym','Gujarati':'guj_Gujr'
+}
+
+CHAT_FILE = "chat_data.json"
+
+@st.cache_resource
+def load_nllb_model():
+    tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-distilled-600M")
+    model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-200-distilled-600M")
+    translator = pipeline('translation', model=model, tokenizer=tokenizer)
+    return translator
+
+@st.cache_resource
+def load_sentence_model():
+    return SentenceTransformer("google/muril-base-cased")
+
+translator_nllb = load_nllb_model()
+sentence_model = load_sentence_model()
+
+def load_messages():
+    try:
+        with open(CHAT_FILE, "r") as file:
+            return json.load(file)
+    except (FileNotFoundError, json.JSONDecodeError):
+        return []
+
+def save_messages(messages):
+    with open(CHAT_FILE, "w") as file:
+        json.dump(messages, file)
+
+def translate_text_multimodel(text, source_lang_name, target_lang_name):
+    source_nllb = nllb_langs[source_lang_name]
+    target_nllb = nllb_langs[target_lang_name]
+
+    # NLLB Translation
+    translation_nllb = translator_nllb(text, src_lang=source_nllb, tgt_lang=target_nllb)[0]['translation_text']
+    print(translation_nllb)
+    # Google Translation
+    translation_google = GoogleTranslator(source='auto', target=language_dict[target_lang_name]).translate(text)
+
+    # Cosine similarity comparison
+    embedding_original = sentence_model.encode(text, convert_to_tensor=True)
+    embedding_nllb = sentence_model.encode(translation_nllb, convert_to_tensor=True)
+    embedding_google = sentence_model.encode(translation_google, convert_to_tensor=True)
+
+    cosine_score_nllb = util.cos_sim(embedding_original, embedding_nllb).item()
+    cosine_score_google = util.cos_sim(embedding_original, embedding_google).item()
+
+    # Select more accurate translation
+    if cosine_score_nllb >= cosine_score_google:
+        print('nllb')
+        return translation_nllb
+    else:
+        print('gt')
+        return translation_google
+
+def main():
+    
+    st.title("Multilingual Chat Application with Speech Input")
+
+    # Sidebar for user setup
+    st.sidebar.header("User Setup")
+    username = st.sidebar.text_input("Enter your name:")
+    language = st.sidebar.selectbox("Choose your language:", list(language_dict.keys()))
+    
+    if not username:
+        st.warning("Please enter your name to start chatting.")
+        return
+
+    user_lang_code = language_dict[language]
+
+    if "messages" not in st.session_state:
+        st.session_state["messages"] = load_messages()
+
+    # Display chat history
+    st.subheader("Chat Room")
+    
+    # chat_container = st.container()
+    
+    # with chat_container:
+    for msg in st.session_state["messages"]:
+            # translated_text = GoogleTranslator(source='auto', target=user_lang_code).translate(msg['text'])
+            #translated_text
+        with st.chat_message(msg['name']):
+            st.write(f"{msg['name']} ({msg['lang']}): {msg['translations'][language]}")
+
+    # Speech input integration
+    st.subheader("Speak your message")
+    
+    spoken_text = speech_to_text(language=user_lang_code, use_container_width=True, just_once=True, key='speech_input')
+
+    if spoken_text:
+        input_text = spoken_text
+        translations = {}
+        st.write(f"You said: {spoken_text}")
+
+        if spoken_text:
+            for lang in nllb_langs:
+                translation = translate_text_multimodel(spoken_text, language, lang)
+                translations[lang] = translation
+            new_message = {"user": username, "name": username, "lang": language, "text": input_text, "translations": translations}
+            st.session_state["messages"].append(new_message)
+            save_messages(st.session_state["messages"])
+            st.rerun()
+    time.sleep(1)
+    st.rerun()
+
+
+
+
+
+
+if __name__ == "__main__":
+   main()