Update app.py

app.py

@@ -1,129 +1,65 @@
 import os
-import sys
+from typing import Optional
 import gradio as gr
-import numpy as np
-import torch
-import subprocess
-import shutil
-from pathlib import Path
+from synthesis import synthesize_text
 
-# Model repository information
-REPO_URL = "https://github.com/hpbyte/myanmar-tts.git"
-MODEL_DIR = "trained_model"
-REPO_DIR = "myanmar-tts"
+# Configure correct paths
+MODEL_DIR = os.path.join(os.path.dirname(__file__), "trained_model")
+MODEL_PATH = os.path.join(MODEL_DIR, "checkpoint_latest.pth.tar")
+HPARAMS_PATH = os.path.join(MODEL_DIR, "hparams.yml")
 
-# Check and install the package if not already installed
-def setup_environment():
-    status_msg = ""
+# Check if model files exist
+if not os.path.exists(MODEL_PATH):
+    print(f"ERROR: Model checkpoint not found at {MODEL_PATH}")
     
-    # Clone the repository if it doesn't exist
-    if not os.path.exists(REPO_DIR):
-        status_msg += "Cloning repository...\n"
-        subprocess.run(["git", "clone", REPO_URL], check=True)
-    
-    # Add the repository to Python path
-    repo_path = os.path.abspath(REPO_DIR)
-    if repo_path not in sys.path:
-        sys.path.append(repo_path)
-        status_msg += f"Added {repo_path} to Python path\n"
-    
-    # Create model directory if it doesn't exist
-    if not os.path.exists(MODEL_DIR):
-        os.makedirs(MODEL_DIR)
-        status_msg += f"Created {MODEL_DIR} directory\n"
-    
-    return status_msg + "Environment setup complete"
+if not os.path.exists(HPARAMS_PATH):
+    print(f"ERROR: Hyperparameters file not found at {HPARAMS_PATH}")
 
-# Function to synthesize speech
-def synthesize_speech(text):
+# Synthesis function wrapper
+def generate_speech(text: str) -> Optional[str]:
     try:
-        # Import necessary modules from the repository
-        sys.path.append(REPO_DIR)
-        from myanmar_tts.text import text_to_sequence
-        from myanmar_tts.utils.hparams import create_hparams
-        from myanmar_tts.train import load_model
-        from myanmar_tts.synthesis import generate_speech
-        import scipy.io.wavfile
-        
-        # Check if model exists, if not provide instructions
-        checkpoint_path = os.path.join(MODEL_DIR, "checkpoint_latest.pth.tar")
-        config_path = os.path.join(MODEL_DIR, "hparams.yml")
-        
-        if not os.path.exists(checkpoint_path) or not os.path.exists(config_path):
-            return None, f"""Model files not found. Please upload:
-1. The checkpoint file at: {checkpoint_path}
-2. The hparams.yml file at: {config_path}
-
-You can obtain these files from the original repository or by training the model."""
-        
-        # Load the model and hyperparameters
-        hparams = create_hparams(config_path)
-        model = load_model(hparams)
-        model.load_state_dict(torch.load(checkpoint_path, map_location=torch.device('cpu'))['state_dict'])
-        model.eval()
-        
-        # Process text input
-        sequence = np.array(text_to_sequence(text, ['burmese_cleaners']))[None, :]
-        sequence = torch.autograd.Variable(torch.from_numpy(sequence)).cpu().long()
-        
-        # Generate mel spectrograms
-        mel_outputs, mel_outputs_postnet, _, alignments = model.inference(sequence)
-        
-        # Generate waveform
-        with torch.no_grad():
-            waveform = generate_speech(mel_outputs_postnet, hparams)
-        
-        # Save and return the audio
-        output_path = "output.wav"
-        scipy.io.wavfile.write(output_path, hparams.sampling_rate, waveform)
-        
-        return output_path, "Speech generated successfully!"
-    
+        if not text.strip():
+            return None
+            
+        # Pass correct paths to the synthesis function
+        audio_output = synthesize_text(
+            text, 
+            checkpoint_path=MODEL_PATH,
+            hparams_path=HPARAMS_PATH
+        )
+        return audio_output
     except Exception as e:
-        return None, f"Error: {str(e)}\n\nMake sure you have uploaded the model files to the {MODEL_DIR} directory."
+        print(f"Error generating speech: {str(e)}")
+        return None
 
-# Function for the Gradio interface
-def tts_interface(text):
-    if not text.strip():
-        return None, "Please enter some text."
+# Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# Myanmar Text-to-Speech Demo")
     
-    return synthesize_speech(text)
-
-# Set up the environment
-setup_message = setup_environment()
-print(setup_message)
-
-# Create the Gradio interface
-demo = gr.Interface(
-    fn=tts_interface,
-    inputs=[
-        gr.Textbox(
-            lines=3, 
-            placeholder="Enter Burmese text here...", 
-            label="Text"
-        )
-    ],
-    outputs=[
-        gr.Audio(label="Generated Speech"),
-        gr.Textbox(label="Status")
-    ],
-    title="Myanmar (Burmese) Text-to-Speech",
-    description="""
-    This is a demo of the Myanmar Text-to-Speech system developed by hpbyte.
-    Enter Burmese text in the box below and click 'Submit' to generate speech.
+    with gr.Row():
+        with gr.Column():
+            text_input = gr.Textbox(
+                label="Enter Myanmar text",
+                placeholder="မြန်မာစာ ရိုက်ထည့်ပါ",
+                lines=3
+            )
+            submit_btn = gr.Button("Generate Speech")
+            
+        with gr.Column():
+            audio_output = gr.Audio(label="Generated Speech")
     
-    **Note:** You need to upload the model files to the 'trained_model' directory:
-    - checkpoint_latest.pth.tar
-    - hparams.yml
+    submit_btn.click(
+        fn=generate_speech,
+        inputs=text_input,
+        outputs=audio_output
+    )
     
-    GitHub Repository: https://github.com/hpbyte/myanmar-tts
-    """,
-    examples=[
-        ["မင်္ဂလာပါ"],
-        ["မြန်မာစကားပြောစနစ်ကို ကြိုဆိုပါတယ်"],
-        ["ဒီစနစ်ဟာ မြန်မာစာကို အသံအဖြစ် ပြောင်းပေးနိုင်ပါတယ်"],
-    ]
-)
+    gr.Markdown("""
+    ## Example Phrases
+    - မင်္ဂလာပါ (Hello)
+    - မြန်မာစကားပြောစနစ်ကို ကြိုဆိုပါတယ် (Welcome to the Myanmar speech system)
+    - ဒီစနစ်ဟာ မြန်မာစာကို အသံအဖြစ် ပြောင်းပေးနိုင်ပါတယ် (This system can convert Myanmar text to speech)
+    """)
 
 # Launch the app
 if __name__ == "__main__":