Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import whisper | |
| import numpy as np | |
| import sounddevice as sd | |
| import tempfile | |
| import os | |
| import io | |
| # Load Whisper model | |
| model = whisper.load_model("base") # You can choose a larger model if needed | |
| # Real-time audio recording | |
| def record_audio(duration=5, samplerate=16000): | |
| st.write("Recording...") | |
| audio = sd.rec(int(duration * samplerate), samplerate=samplerate, channels=1, dtype='int16') | |
| sd.wait() | |
| return audio.flatten() | |
| # Convert recorded audio to WAV format | |
| def audio_to_wav(audio, samplerate=16000): | |
| temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.wav') | |
| with open(temp_file.name, 'wb') as f: | |
| f.write(audio) | |
| return temp_file.name | |
| # Function to transcribe audio using Whisper | |
| def transcribe_audio(audio): | |
| result = model.transcribe(audio) | |
| return result['text'] | |
| # Streamlit interface | |
| st.title("Text/Audio Translator") | |
| # Recording button | |
| if st.button("Record"): | |
| audio = record_audio(duration=5) # Record for 5 seconds | |
| st.write("Processing audio...") | |
| wav_path = audio_to_wav(audio) | |
| transcription = transcribe_audio(wav_path) | |
| st.write("Transcription:", transcription) | |
| # Text Input | |
| text_input = st.text_area("Or enter text in English:") | |
| # Language Translation | |
| translator = None | |
| if text_input or transcription: | |
| st.write("Translating text...") | |
| # Select the language to translate into | |
| target_language = st.selectbox( | |
| "Select target language:", | |
| ["French", "Chinese", "Italian", "Urdu", "Hindi", "Punjabi", "Saraiki", "Pashto"] | |
| ) | |
| # Choose the correct translation model based on the selected language | |
| if target_language == "French": | |
| translator = pipeline("translation", model="Helsinki-NLP/opus-mt-en-fr") | |
| elif target_language == "Chinese": | |
| translator = pipeline("translation", model="Helsinki-NLP/opus-mt-en-zh") | |
| elif target_language == "Italian": | |
| translator = pipeline("translation", model="Helsinki-NLP/opus-mt-en-it") | |
| elif target_language == "Urdu": | |
| translator = pipeline("translation", model="Helsinki-NLP/opus-mt-en-ur") | |
| elif target_language == "Hindi": | |
| translator = pipeline("translation", model="Helsinki-NLP/opus-mt-en-hi") | |
| elif target_language == "Punjabi": | |
| translator = pipeline("translation", model="Helsinki-NLP/opus-mt-en-pa") | |
| elif target_language == "Saraiki": | |
| st.write("Saraiki model not available.") | |
| elif target_language == "Pashto": | |
| st.write("Pashto model not available.") | |
| if translator: | |
| text = text_input or transcription | |
| translated_text = translator(text) | |
| st.write("Translated Text:", translated_text[0]['translation_text']) | |
| # Text-to-Speech | |
| if translator: | |
| st.write("Generating speech...") | |
| tts = pipeline("text-to-speech", model="microsoft/speecht5_tts") | |
| tts_audio = tts(translated_text[0]['translation_text'])[0] | |
| st.audio(tts_audio, format="audio/wav") | |