Create app.py

app.py

@@ -0,0 +1,45 @@
+import streamlit as st  # Make sure to import streamlit
+import torch
+from transformers import MarianMTModel, MarianTokenizer
+import speech_recognition as sr
+from gtts import gTTS
+import os
+
+# Function to recognize speech from an audio file
+def recognize_speech_from_file(audio_file):
+    recognizer = sr.Recognizer()
+    with sr.AudioFile(audio_file) as source:
+        audio = recognizer.record(source)
+    try:
+        return recognizer.recognize_google(audio)
+    except sr.UnknownValueError:
+        return "Could not understand audio"
+    except sr.RequestError:
+        return "Could not request results; check your internet connection"
+
+# Function to translate text
+def translate_text(text):
+    model_name = "Helsinki-NLP/opus-mt-en-hi"
+    tokenizer = MarianTokenizer.from_pretrained(model_name)
+    model = MarianMTModel.from_pretrained(model_name)
+    translated = model.generate(**tokenizer(text, return_tensors="pt", padding=True))
+    return tokenizer.decode(translated[0], skip_special_tokens=True)
+
+# Function to convert text to audio
+def convert_to_audio(text):
+    tts = gTTS(text, lang="hi")
+    audio_output = "output.mp3"
+    tts.save(audio_output)
+    return audio_output
+
+st.title("English to Hindi Audio Translation")
+
+# Make the translation service available without time restrictions
+audio_file = st.file_uploader("Upload an audio file", type=["wav", "mp3"])
+if audio_file is not None:
+    text = recognize_speech_from_file(audio_file)
+    st.write(f"Recognized English Text: {text}")
+    translated_text = translate_text(text)
+    st.write(f"Translated Hindi Text: {translated_text}")
+    audio_output = convert_to_audio(translated_text)
+    st.audio(audio_output, format='audio/mp3')