| import streamlit as st |
| import torch |
| from transformers import MarianMTModel, MarianTokenizer |
| import speech_recognition as sr |
| from gtts import gTTS |
| import os |
|
|
| |
| 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" |
|
|
| |
| 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) |
|
|
| |
| 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") |
|
|
| |
| 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') |
|
|
