Update handler.py

handler.py

@@ -6,6 +6,50 @@ import base64
 import numpy as np
 import librosa
 from scipy.io import wavfile
+import asyncio
+import zipfile
+import requests
+
+
+def download_and_extract_files():
+    files_to_download = [
+        ("config.py", "https://www.dropbox.com/scl/fi/3vnj2myor659x5xyteu6u/config.py?rlkey=h7z6mp7denazoqwtr5hj0g70n&st=2vop5eid&dl=1"),
+        ("hubert_base.pt", "https://www.dropbox.com/scl/fi/g7oohuwfzlnrbd8zic6gj/hubert_base.pt?rlkey=ddeyqex1morsm54azyakmd62e&st=s7p2ocr3&dl=1"),
+        ("lib.zip", "https://www.dropbox.com/scl/fi/ia6p6cf5xvcbi78dmkbbz/lib.zip?rlkey=k3chc1nlaswsqdo7slqco56wi&st=re40dqki&dl=1"),
+        ("rmvpe.pt", "https://www.dropbox.com/scl/fi/7pl7u6fvydwgtz19n8nzx/rmvpe.pt?rlkey=tnbxmarogivbw3qy34hgy7r7q&st=69iglyfn&dl=1"),
+        ("rmvpe.py", "https://www.dropbox.com/scl/fi/i2shk4otwyg4ns8yod5h1/rmvpe.py?rlkey=l7313htdh1ihylb6bx91el0lv&st=mrz8advb&dl=1"),
+        ("vc_infer_pipeline.py", "https://www.dropbox.com/scl/fi/k0hbva7vujhbmzg2l0l2g/vc_infer_pipeline.py?rlkey=5leclgbjiv6ukjywnftscnwe8&st=fj6sgnq4&dl=1"),
+        ("voice_processing.py", "https://www.dropbox.com/scl/fi/z6gyjaymlgwinst05bb43/voice_processing.py?rlkey=0qlcfv6g9db2uzaq3xvv6k43s&st=gg63oppb&dl=1"),
+        ("weights.zip", "https://www.dropbox.com/scl/fi/tr5a04wlow5go8cv3d6qp/weights.zip?rlkey=qvpwax97nn5a4iv79g76lcbz2&st=5ueb2gva&dl=1")
+    ]
+
+    for file_name, url in files_to_download:
+        if not os.path.exists(file_name):
+            response = requests.get(url)
+            with open(file_name, "wb") as file:
+                file.write(response.content)
+
+            if file_name.endswith(".zip"):
+                with zipfile.ZipFile(file_name, "r") as zip_ref:
+                    extract_to = os.path.splitext(file_name)[0]
+                    for member in zip_ref.namelist():
+                        # Extract files into the target directory without the first part of the path
+                        member_path = os.path.join(extract_to, *member.split('/')[1:])
+                        if member.endswith('/'):
+                            os.makedirs(member_path, exist_ok=True)
+                        else:
+                            os.makedirs(os.path.dirname(member_path), exist_ok=True)
+                            with open(member_path, 'wb') as f:
+                                f.write(zip_ref.read(member))
+
+                # Optionally, remove the zip file after extraction
+                os.remove(file_name)
+
+# Run the function
+download_and_extract_files()
+
+from voice_processing import tts, get_model_names, voice_mapping, get_unique_filename
+
 
 class EndpointHandler:
     def __init__(self, model_dir=None):
@@ -13,25 +57,10 @@ class EndpointHandler:
 
     def __call__(self, data: Dict[str, Any]) -> Dict[str, Any]:
         try:
-            # Extract the actual input data from the "inputs" field
-            if "inputs" in data:
-                json_data = data["inputs"]
+            if "inputs" in data:  # Check if data is in Hugging Face JSON format
+                return self.process_hf_input(data)
             else:
-                json_data = data
-
-            # Clone the repository if it's not already cloned
-            repo_dir = "TTS_Mongolian"
-            if not os.path.exists(repo_dir):
-                repo_url = "https://huggingface.co/mazalaai/TTS_Mongolian.git"
-                os.system(f"git clone {repo_url}")
-
-            # Change directory to the repository
-            os.chdir(repo_dir)
-
-            # Import the voice_processing module and functions
-            from voice_processing import tts, get_model_names, voice_mapping, get_unique_filename
-
-            return self.process_json_input(json_data)
+                return self.process_json_input(data)
         except ValueError as e:
             return {"error": str(e)}
         except Exception as e:
@@ -50,13 +79,15 @@ class EndpointHandler:
             if not edge_tts_voice:
                 raise ValueError(f"Invalid voice '{selected_voice}'.")
 
-            info, edge_tts_output_path, tts_output_data, edge_output_file = tts(
+            info, edge_tts_output_path, tts_output_data, edge_output_file = asyncio.run(tts(
                 model_name, tts_text, edge_tts_voice, slang_rate, use_uploaded_voice, voice_upload_file
-            )
+            ))
+
             if edge_output_file and os.path.exists(edge_output_file):
                 os.remove(edge_output_file)
 
             _, audio_output = tts_output_data
+
             audio_file_path = self.save_audio_data_to_file(audio_output) if isinstance(audio_output, np.ndarray) else audio_output
 
             try:
@@ -73,6 +104,13 @@ class EndpointHandler:
         else:
             raise ValueError("Invalid JSON structure.")
 
+    def process_hf_input(self, hf_data):
+        if "inputs" in hf_data:
+            actual_data = hf_data["inputs"]
+            return self.process_json_input(actual_data)
+        else:
+            return {"error": "Invalid Hugging Face JSON structure."}
+
     def save_audio_data_to_file(self, audio_data, sample_rate=40000):
         file_path = get_unique_filename('wav')
         wavfile.write(file_path, sample_rate, audio_data)