Spaces:
Running
Running
File size: 4,663 Bytes
cd1309d 2d2f2b9 cd1309d 2d2f2b9 cd1309d 2d2f2b9 cd1309d 2d2f2b9 cd1309d 2d2f2b9 cd1309d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 |
"""
Main entry point for the Audio Translation Web Application
Handles file upload, processing pipeline, and UI rendering
"""
import streamlit as st
import os
import time
import subprocess
from utils.stt import transcribe_audio
from utils.translation import translate_text
from utils.tts import generate_speech
# Hugging Face Spaces Setup Automation
def setup_huggingface_space():
"""Automatically configure Hugging Face Space requirements"""
st.sidebar.header("Space Configuration")
# Check for required system packages
try:
subprocess.run(["espeak-ng", "--version"], check=True, capture_output=True)
except (FileNotFoundError, subprocess.CalledProcessError):
st.sidebar.error("""
**Missing System Dependencies!** Add this to your Space settings:
```txt
apt-get update && apt-get install -y espeak-ng
```
""")
st.stop()
# Verify model files
model_dir = "./kokoro"
required_files = [
f"{model_dir}/kokoro-v0_19.pth",
f"{model_dir}/voices/af_bella.pt"
]
if not all(os.path.exists(f) for f in required_files):
st.sidebar.warning("""
**Missing Model Files!** Add this to your Space settings:
```txt
git clone https://huggingface.co/hexgrad/Kokoro-82M ./kokoro
```
""")
st.stop()
# Initialize environment configurations
os.makedirs("temp/uploads", exist_ok=True)
os.makedirs("temp/outputs", exist_ok=True)
def configure_page():
"""Set up Streamlit page configuration"""
st.set_page_config(
page_title="Audio Translator",
page_icon="🎧",
layout="wide",
initial_sidebar_state="expanded"
)
st.markdown("""
<style>
.reportview-container {margin-top: -2em;}
#MainMenu {visibility: hidden;}
.stDeployButton {display:none;}
.stAlert {padding: 20px !important;}
</style>
""", unsafe_allow_html=True)
def handle_file_processing(upload_path):
"""
Execute the complete processing pipeline:
1. Speech-to-Text (STT)
2. Machine Translation
3. Text-to-Speech (TTS)
"""
progress_bar = st.progress(0)
status_text = st.empty()
try:
# STT Phase
status_text.markdown("🔍 **Performing Speech Recognition...**")
english_text = transcribe_audio(upload_path)
progress_bar.progress(30)
# Translation Phase
status_text.markdown("🌐 **Translating Content...**")
chinese_text = translate_text(english_text)
progress_bar.progress(60)
# TTS Phase
status_text.markdown("🎵 **Generating Chinese Speech...**")
output_path = generate_speech(chinese_text, language="zh")
progress_bar.progress(100)
# Display results
status_text.success("✅ Processing Complete!")
return english_text, chinese_text, output_path
except Exception as e:
status_text.error(f"❌ Processing Failed: {str(e)}")
st.exception(e)
raise
def render_results(english_text, chinese_text, output_path):
"""Display processing results in organized columns"""
st.divider()
col1, col2 = st.columns([2, 1])
with col1:
st.subheader("Recognition Results")
st.code(english_text, language="text")
st.subheader("Translation Results")
st.code(chinese_text, language="text")
with col2:
st.subheader("Audio Output")
st.audio(output_path)
with open(output_path, "rb") as f:
st.download_button(
label="Download Audio",
data=f,
file_name="translated_audio.wav",
mime="audio/wav"
)
def main():
"""Main application workflow"""
setup_huggingface_space() # First-run configuration checks
configure_page()
st.title("🎧 High-Quality Audio Translation System")
st.markdown("Upload English Audio → Get Chinese Speech Output")
# File uploader widget
uploaded_file = st.file_uploader(
"Select Audio File (MP3/WAV)",
type=["mp3", "wav"],
accept_multiple_files=False
)
if uploaded_file:
# Save uploaded file
upload_path = os.path.join("temp/uploads", uploaded_file.name)
with open(upload_path, "wb") as f:
f.write(uploaded_file.getbuffer())
# Execute processing pipeline
results = handle_file_processing(upload_path)
if results:
render_results(*results)
if __name__ == "__main__":
main() |