Upload 8 files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* 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
+fevicon.png filter=lfs diff=lfs merge=lfs -text
+logo.png filter=lfs diff=lfs merge=lfs -text

about.py

@@ -0,0 +1,39 @@
+import streamlit as st
+
+def about_page():
+    st.title("📌 About VoiceBridge")
+    
+    st.markdown("""
+    **VoiceBridge** is a smart and user-friendly app designed to help you **translate speech or text across multiple languages** and analyze the **emotional tone** of the message.
+
+    ---
+    ### 🚀 What Can VoiceBridge Do?
+    - 🗣️ Convert **voice to text** using speech recognition
+    - 🌐 Translate text or speech into other languages using Deep Translator (Google Translate)
+    - 💬 Detect the **sentiment or tone** of the message using local and cloud-based models
+
+    ---
+    ### 🔧 Technologies Used
+    - **Speech Recognition**: `speech_recognition` library for converting audio to text
+    - **Translation**: `deep_translator` with Google Translate for accurate text translation
+    - **Sentiment Analysis**:
+        - For text: Hugging Face Transformer models (e.g., BERT-based sentiment classification)
+        - For voice: A local emotion detection model to analyze audio tone
+
+    ---
+    ### 🎯 Why VoiceBridge?
+    VoiceBridge is created to:
+    - Break language barriers in real-time
+    - Help understand the emotional intent of communication
+    - Enable better interaction in global, multicultural environments
+    - Support accessibility and learning
+
+    ---
+    ### 👨‍💻 Developer Info
+    **Developed by**: Ayush & Manav
+    🔗 [GitHub](https://github.com/yourusername) | [LinkedIn](https://linkedin.com/in/yourprofile)
+
+    ---
+    🌐 VoiceBridge is open for collaboration and feedback. Let's bridge the gap between voices and languages! 💬🌍
+    """)
+

app1.py

@@ -0,0 +1,216 @@
+import streamlit as st 
+from deep_translator import GoogleTranslator
+from gtts import gTTS
+from pydub import AudioSegment
+import tempfile
+import os
+import speech_recognition as sr
+from transformers import pipeline as pl
+from streamlit_option_menu import option_menu
+import css
+from st_audiorec import st_audiorec
+import streamlit.components.v1 as components
+from voice import transcribe,text_to_speech
+from tone import tone
+import about
+
+os.environ["STREAMLIT_WATCHER_TYPE"] = "none"
+st.session_state.translate=False
+
+st.set_page_config(page_title="VoiceBridge",layout="wide",page_icon="fevicon.png")
+Languages = {'afrikaans':'af','albanian':'sq','amharic':'am','arabic':'ar','armenian':'hy','azerbaijani':'az',
+             'basque':'eu','belarusian':'be','bengali':'bn','bosnian':'bs','bulgarian':'bg','catalan':'ca',
+             'cebuano':'ceb','chichewa':'ny','chinese (simplified)':'zh-cn','chinese (traditional)':'zh-tw',
+             'corsican':'co','croatian':'hr','czech':'cs','danish':'da','dutch':'nl','english':'en','esperanto':'eo',
+             'estonian':'et','filipino':'tl','finnish':'fi','french':'fr','frisian':'fy','galician':'gl','georgian':'ka',
+             'german':'de','greek':'el','gujarati':'gu','haitian creole':'ht','hausa':'ha','hawaiian':'haw','hebrew':'iw',
+             'hebrew':'he','hindi':'hi','hmong':'hmn','hungarian':'hu','icelandic':'is','igbo':'ig','indonesian':'id',
+             'irish':'ga','italian':'it','japanese':'ja','javanese':'jw','kannada':'kn','kazakh':'kk','khmer':'km',
+             'korean':'ko','kurdish (kurmanji)':'ku','kyrgyz':'ky','lao':'lo','latin':'la','latvian':'lv','lithuanian':'lt',
+             'luxembourgish':'lb','macedonian':'mk','malagasy':'mg','malay':'ms','malayalam':'ml','maltese':'mt','maori':'mi',
+             'marathi':'mr','mongolian':'mn','myanmar (burmese)':'my','nepali':'ne','norwegian':'no','odia':'or','pashto':'ps',
+             'persian':'fa','polish':'pl','portuguese':'pt','punjabi':'pa','romanian':'ro','russian':'ru','samoan':'sm',
+             'scots gaelic':'gd','serbian':'sr','sesotho':'st','shona':'sn','sindhi':'sd','sinhala':'si','slovak':'sk',
+             'slovenian':'sl','somali':'so','spanish':'es','sundanese':'su','swahili':'sw','swedish':'sv','tajik':'tg',
+             'tamil':'ta','telugu':'te','thai':'th','turkish':'tr','turkmen':'tk','ukrainian':'uk','urdu':'ur','uyghur':'ug',
+             'uzbek':'uz','vietnamese':'vi','welsh':'cy','xhosa':'xh','yiddish':'yi','yoruba':'yo','zulu':'zu'}
+
+
+
+st.markdown(
+    """
+    <style>
+
+    [alt="Logo"] {
+        height: 90px;
+        width: auto;  
+        
+    }
+    .block-container {
+            padding-top: 0rem;
+        }
+    header { visibility: hidden; }
+    </style>
+    """,
+    unsafe_allow_html=True
+)
+col1, col2 = st.columns([1, 6])
+with col1:
+    st.markdown("""
+    <style>
+    @media only screen and (max-width: 959px) {
+        img {
+            max-width: 100px;
+            height: auto;
+        }
+    }
+    </style>
+    """, unsafe_allow_html=True)
+    st.logo("logo.png")
+with col2:
+
+    css.nev()
+    st.markdown('<div class="custom-navbar">', unsafe_allow_html=True)
+    selected = option_menu(
+        menu_title=None,
+        options=["Translate", "Tone", "About"],
+        icons=["bi-people-fill", "bi-soundwave", "gear"],
+        menu_icon="cast",
+        default_index=0,
+        orientation="horizontal",
+        styles={
+            "container": {"padding": "0!important", "background-color": "#0E1117"},
+            "icon": {"color": "white"},
+            "nav-link": {
+                "text-align": "center",
+                "margin": "0px",
+                "--hover-color": "#204044",
+            },
+            "nav-link-selected": {"background-color": "#1f6f78"},
+        }
+    )
+    st.markdown('</div>', unsafe_allow_html=True)
+with st.container():
+    st.markdown("""
+    <style>
+    .custom-container {
+        margin-top: 70px;
+    }
+
+    @media (max-width: 767px) {
+        .custom-container {
+            margin-top: 0px;
+        }
+    }
+    </style>
+    <style>
+    .middle {
+        margin-top: 120px;
+    }
+
+    @media (max-width: 767px) {
+        .middle {
+            margin-top: 0px;
+        }
+    }
+    </style>
+""", unsafe_allow_html=True)
+    st.markdown('<div class="custom-container">', unsafe_allow_html=True)
+
+    left_col, st.session_state.mid_col, st.session_state.right_col = st.columns([3, 2, 3])
+    # left user input
+    # ------------------------------------------------------------------------------------------------------------------------------------------------
+    if (selected == "Translate" or selected == "Tone"):
+        with left_col:
+            with st.popover("", icon=":material/tune:"):
+                inp = st.selectbox('Choose Input Format', ("Text", "Audio_file", "MIC"))
+                st.session_state.inp = inp
+            with st.form("my_form"):
+                st.markdown("### 🎙️ Input")
+                if st.session_state.inp == "Text":
+                    st.session_state.text = st.text_area("Enter Text:", help="Type your text here...")
+                elif st.session_state.inp == "MIC":
+                    st.session_state.uploaded_file = st.audio_input("Record a Voice Message")
+                else:
+                    st.session_state.uploaded_file = st.file_uploader("Upload an Audio File", type=["mp3", "wav", "m4a"])
+                    
+                submitted = st.form_submit_button("Submit")
+    
+        # ------------------------------------------------------------------------------------------------------------------------------------------------
+    if selected == "Translate":            
+        
+        # ------------------------------------------------------------------------------------------------------------------------------------------------
+        # center button
+        st.markdown('<div class="middle">', unsafe_allow_html=True)
+        with st.session_state.mid_col:
+            
+            css.cicle_button()
+            
+            if st.button("Translate"):
+                st.session_state.translate=False
+                st.session_state.translate=True
+        st.markdown('</div>', unsafe_allow_html=True)
+
+
+        # ------------------------------------------------------------------------------------------------------------------------------------------------
+        # Right Output
+        with st.session_state.right_col:
+            
+            with st.popover("", icon=":material/tune:"):
+                out_type = st.selectbox('Choose Input Format', ("Text", "Voice", "Both"))
+                st.session_state.out_type = out_type
+            with st.form("output"):
+                st.markdown("### 🔉 Voice Output")
+                option2 = st.selectbox('Select Output Language', list(Languages.keys()))
+                value2 = Languages[option2]
+                
+                if st.session_state.translate:
+                    c1,c2=st.columns(2)
+                    if st.session_state.inp != "Text":
+                        st.session_state.text = transcribe(st.session_state.uploaded_file)
+                        
+                    translated_text = GoogleTranslator(target=value2).translate(st.session_state.text)
+                    
+                    if st.session_state.out_type == "Text":
+                        st.text_area("Translated Text:", translated_text, height=100)
+
+                    elif st.session_state.out_type == "Voice":
+                        if translated_text.strip():
+                            audio_file = text_to_speech(translated_text, value2)
+                        else:
+                            c2.warning("Please enter text before converting.")
+                        st.audio(audio_file, format='audio/mp3', autoplay=True)
+
+                    else:
+                        if translated_text.strip():
+                            audio_file = text_to_speech(translated_text, value2)
+                        else:
+                            c2.warning("Please enter text before converting.")
+                        with c1.popover("", icon=":material/library_books:"):
+                            st.text_area("Translated Text:", translated_text, height=100)
+                        c2.audio(audio_file, format='audio/mp3', autoplay=True)
+
+                reset = st.form_submit_button("Reset ↻ ")
+                if reset:
+                    st.session_state.translate= False
+        # Optional: Add some styling
+        st.markdown("""
+                    
+        <style>
+        body {
+            background-color: #0e1117;
+            color: white;
+        }
+        .stButton>button {
+            background-color: teal;
+            color: white;
+        }
+        </style>
+    """, unsafe_allow_html=True)
+        st.markdown('</div>', unsafe_allow_html=True)
+
+
+    if selected == "Tone":
+        tone()
+    if selected == "About":
+        about.about_page()

css.py

@@ -0,0 +1,85 @@
+import streamlit as st
+
+def nev():
+    st.markdown("""
+        <style>
+        /* Responsive icon and text size for option menu */
+        @media only screen and (max-width: 768px) {
+            .nav-link > span {
+                font-size: 14px !important; /* reduce label size */
+            }
+            .nav-link > i {
+                font-size: 16px !important; /* reduce icon size */
+            }
+        }
+
+        @media only screen and (max-width: 480px) {
+            .nav-link > span {
+                font-size: 12px !important;
+            }
+            .nav-link > i {
+                font-size: 14px !important;
+            }
+        }
+
+        @media only screen and (min-width: 769px) {
+            .nav-link > span {
+                font-size: 18px !important;
+            }
+            .nav-link > i {
+                font-size: 20px !important;
+            }
+        }
+
+        .custom-navbar {
+            margin-top: 0px;
+        }
+
+        @media only screen and (max-width: 768px) {
+            .custom-navbar {
+                margin-top: 50px !important;
+            }
+        }
+        </style>
+    """, unsafe_allow_html=True)
+
+def cicle_button():
+    st.markdown("""
+        <style>
+        /* Target the button using Streamlit's internal structure */
+        div[class^="stButton"] > button {
+            width: 80px;
+            height: 80px;
+            border-radius: 50%;
+            background-color: #008080;
+            color: white;
+            font-weight: bold;
+            font-size: 16px;
+            padding: 0;
+            border: none;
+            margin-left: 37%;
+            margin-top: 70px;
+        }
+        
+        @media (max-width: 640px) {
+        div[class^="stButton"] > button {
+            margin-top: 0px;
+            margin-left:43%;
+            
+        }
+        div[class^="stButton"] > button:hover {
+            background-color: #009999;
+            margin-left: 90px;
+        }
+        @media (max-width: 767px) {
+        div[class^="stButton"] > button:hover{
+            margin-top: 0px;
+            margin-left:60px;   
+        }
+        @media (max-width: 640px) {
+        div[class^="stButton"] > button:hover{
+            margin-top: 0px;
+            margin-left:43%;   
+        }
+        </style>
+        """, unsafe_allow_html=True)

requirements.txt

@@ -0,0 +1,8 @@
+streamlit
+deep-translator
+gTTS
+pydub
+speechrecognition
+transformers
+streamlit-option-menu
+st-audiorec

tone.py

@@ -0,0 +1,95 @@
+import streamlit as st 
+from deep_translator import GoogleTranslator
+from gtts import gTTS
+from pydub import AudioSegment
+import tempfile
+import os
+import speech_recognition as sr
+import css
+from voice import transcribe
+from transformers import pipeline as pl
+# from speechbrain.pretrained import EncoderClassifier
+
+# @st.cache_resource
+# def load_emotion_model():
+#     return EncoderClassifier.from_hparams(
+#         source="emotion_model_local",
+#         savedir="tmp_emotion_model"
+#     )
+
+# emotion_model = load_emotion_model()
+
+# def detect_emotion(uploaded_file):
+#     # Save the uploaded file temporarily
+#     # Use a more robust way to handle the temporary file lifecycle
+#     with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp_file:
+#         tmp_file.write(uploaded_file.getvalue())
+#         raw_path = tmp_file.name
+
+#     try:
+#         audio = AudioSegment.from_file(raw_path)
+#         audio = audio.set_frame_rate(16000).set_channels(1)
+#         audio.export(raw_path, format="wav")
+
+#         # Predict emotion using the cleaned file
+#         # Ensure the path is passed as a standard string
+#         result = emotion_model.classify_file(str(raw_path))
+#         predicted_emotion = result[3][0]
+#         return predicted_emotion
+#     finally:
+#         # Clean up the temporary file
+#         if os.path.exists(raw_path):
+#             os.remove(raw_path)
+def tone():           
+
+    st.session_state.analyse=False
+    st.markdown('<div class="middle">', unsafe_allow_html=True)
+    with st.session_state.mid_col:
+        
+        css.cicle_button()
+        
+        if st.button("Translate"):
+           st.session_state.analyse=True
+
+    st.markdown('</div>', unsafe_allow_html=True)
+    with st.session_state.right_col:
+        if st.session_state.analyse:
+            if st.session_state.inp != "Text":
+                st.session_state.text = transcribe(st.session_state.uploaded_file)
+            st.write(" ")
+            st.write(" ")
+            st.write(" ")
+            with st.form("Tone_form"):
+                if st.session_state.text !="" and st.session_state.text != " ":
+                    pipe = pl("text-classification", model="tabularisai/multilingual-sentiment-analysis")
+                    sentence = st.session_state.text
+                    result = pipe(sentence)[0] 
+
+                    sentiment = result['label']  
+                    
+                    if sentiment == "Very Negative":
+                        st.error('This is Very Negative', icon="🚨")
+                    elif sentiment == "Negative":
+                        st.error('This is Negative', icon="😭")
+                    elif sentiment == "Neutral":
+                        st.warning('This is Neutral', icon="😐")
+                    elif sentiment == "Positive":
+                        st.success('This is Positive', icon="😊")
+                    else: 
+                        st.success('This is Very Positive', icon="😃")
+                else:
+                    st.warning("write something first")
+                reset = st.form_submit_button("Reset ↻ ")
+                if reset:
+                    st.session_state.analyse= False
+
+
+
+
+
+
+        # if st.session_state.inp != "Text":
+        #     text = transcribe(st.session_state.uploaded_file)
+        #     if text !="" and text != " ":
+        #         emotion = detect_emotion(st.session_state.uploaded_file)
+        #         st.write(f"🎭 Detected Emotion: `{emotion}`")

voice.py

@@ -0,0 +1,41 @@
+import streamlit as st 
+from gtts import gTTS
+from pydub import AudioSegment
+import tempfile
+import os
+import speech_recognition as sr
+
+
+
+def text_to_speech(text, lang='en', c=0):
+    tts = gTTS(text=text, lang=lang)
+    audio_file = f"output{c}.mp3"
+    tts.save(audio_file)
+    return audio_file
+
+def transcribe(uploaded_file):
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmpfile:
+        file_path = tmpfile.name
+        tmpfile.write(uploaded_file.read())
+
+    audio = AudioSegment.from_file(file_path)
+    audio = audio.set_frame_rate(16000).set_channels(1)
+    audio.export(file_path, format="wav")
+
+    recognizer = sr.Recognizer()
+    with sr.AudioFile(file_path) as source:
+        trans=True
+        with st.spinner("Transcribing... Please wait!", show_time=True):
+            if trans:
+                audio_data = recognizer.record(source)
+                try:
+                    text = recognizer.recognize_google(audio_data)
+                    trans=False
+                    return text
+                except sr.UnknownValueError:
+                    st.error("❌ Could not understand the audio.")
+                except sr.RequestError:
+                    st.error("❌ API error. Check internet connection.")
+            
+    os.remove(file_path)
+    return ""