Update app.py

app.py

@@ -1,74 +1,65 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
 import gradio as gr
-import wave
-import numpy as np
-from io import BytesIO
-from huggingface_hub import hf_hub_download
-from piper import PiperVoice 
-from transformers import pipeline
-import hazm
-import typing
+import uvicorn
+import requests
+import os
+from dotenv import load_dotenv
+import threading
 
-normalizer = hazm.Normalizer()
-sent_tokenizer = hazm.SentenceTokenizer()
-word_tokenizer = hazm.WordTokenizer()
+# بارگذاری متغیرهای محیطی از فایل .env
+load_dotenv()
 
-tagger_path = hf_hub_download(repo_id="gyroing/HAZM_POS_TAGGER",  filename="pos_tagger.model")
-tagger = hazm.POSTagger(model=tagger_path)
-model_path = hf_hub_download(repo_id="gyroing/Persian-Piper-Model-gyro", filename="fa_IR-gyro-medium.onnx")
-config_path = hf_hub_download(repo_id="gyroing/Persian-Piper-Model-gyro", filename="fa_IR-gyro-medium.onnx.json")
-voice = PiperVoice.load(model_path, config_path)
+# ایجاد یک اپلیکیشن FastAPI
+app = FastAPI()
 
-def preprocess_text(text: str) -> typing.List[typing.List[str]]:
-        """Split/normalize text into sentences/words with hazm"""
-        text = normalizer.normalize(text)
-        processed_sentences = []
+# تعریف Gradio Interface
+def tts_model(text):
+    # اینجا می‌توانید کد اصلی تبدیل متن به گفتار را قرار دهید.
+    return f"صوت برای متن: {text}"
 
-        for sentence in sent_tokenizer.tokenize(text):
-            words = word_tokenizer.tokenize(sentence)
-            processed_words = fix_words(words)
-            processed_sentences.append(" ".join(processed_words))
-        return  " ".join(processed_sentences)    
-def fix_words(words: typing.List[str]) -> typing.List[str]:
-        fixed_words = []
+# پیکربندی رابط کاربری Gradio
+iface = gr.Interface(
+    fn=tts_model,
+    inputs="text",
+    outputs="audio",
+    title="Text to Speech"
+)
 
-        for word, pos in tagger.tag(words):
-            if pos[-1] == "Z":
-                if word[-1] != "ِ":
-                    if (word[-1] == "ه") and (word[-2] != "ا"):
-                        word += "‌ی"
-                word += "ِ"
-                    
+# مدل داده‌ای برای ورودی متنی در FastAPI
+class TextInput(BaseModel):
+    text: str
 
-            fixed_words.append(word)
+# خواندن URL از فایل .env
+hugging_face_api_url = os.getenv("HUGGING_FACE_SPACE_API_URL")
 
-        return fixed_words
+# روت FastAPI برای تبدیل متن به گفتار
+@app.post("/api/tts/")
+async def convert_text_to_speech(input_text: TextInput):
+    try:
+        # ارسال درخواست به Hugging Face Space API
+        response = requests.post(
+            hugging_face_api_url,
+            json={"text": input_text.text}
+        )
+        
+        if response.status_code == 200:
+            # دریافت و بازگرداندن نتیجه
+            return {"audio": response.content}  # یا هر پردازشی که نیاز دارید
+        else:
+            raise HTTPException(status_code=response.status_code, detail="Error in TTS API")
 
-def synthesize_speech(text):
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
 
+# راه‌اندازی Gradio در یک ترد جداگانه
+def start_gradio():
+    iface.launch(server_name="0.0.0.0", server_port=7860, share=True)
 
-    # Create an in-memory buffer for the WAV file
-    buffer = BytesIO()
-    with wave.open(buffer, 'wb') as wav_file:
-        wav_file.setframerate(voice.config.sample_rate)
-        wav_file.setsampwidth(2)  # 16-bit
-        wav_file.setnchannels(1)  # mono
+if __name__ == "__main__":
+    # اجرای Gradio در یک ترد جداگانه
+    gradio_thread = threading.Thread(target=start_gradio)
+    gradio_thread.start()
 
-        # Synthesize speech
-        eztext = preprocess_text(text)
-        voice.synthesize(eztext, wav_file)
-
-    # Convert buffer to NumPy array for Gradio output
-    buffer.seek(0)
-    audio_data = np.frombuffer(buffer.read(), dtype=np.int16)
-
-    return audio_data.tobytes()
-
-# Using Gradio Blocks
-with gr.Blocks(theme=gr.themes.Base()) as blocks:
-    input_text = gr.Textbox(label="Input")
-    output_audio = gr.Audio(label="Output", type="numpy")
-    submit_button = gr.Button("Synthesize")
-
-    submit_button.click(synthesize_speech, inputs=input_text, outputs=[output_audio])
-# Run the app
-blocks.launch()
+    # اجرای FastAPI
+    uvicorn.run(app, host="0.0.0.0", port=8000)