Added RVC request function to allow upload models from ST. Added parameter --max-content-length=X (Mb) to set server max request data size accordingly if needed.

modules/voice_conversion/rvc_module.py

@@ -19,14 +19,24 @@ from scipy.io import wavfile
 import os
 import io
 
+from py7zr import pack_7zarchive, unpack_7zarchive
+import shutil
+
 DEBUG_PREFIX = "<RVC module>"
 RVC_MODELS_PATH = "data/models/rvc/"
 IGNORED_FILES = [".placeholder"]
 
+TEMP_FOLDER_PATH = "data/tmp/"
+
 RVC_INPUT_PATH = "data/tmp/rvc_input.wav"
 RVC_OUTPUT_PATH ="data/tmp/rvc_output.wav"
 save_file = False
 
+
+# register file format at first.
+shutil.register_archive_format('7zip', pack_7zarchive, description='7zip archive')
+shutil.register_unpack_format('7zip', ['.7z'], unpack_7zarchive)
+
 def rvc_get_models_list():
     """
     Return the list of RVC model in the expected folder
@@ -75,6 +85,55 @@ def rvc_get_models_list():
         print(e)
         abort(500, DEBUG_PREFIX + " Exception occurs while searching for RVC models.")
 
+def rvc_upload_models():
+    """
+    Install RVC models uploaded via ST request
+    - Needs flask MAX_CONTENT_LENGTH to be adapted accordingly
+    """
+    try:
+        request_files = request.files
+        print(DEBUG_PREFIX, "received:", request_files)
+
+        for request_file_name in request_files:
+            zip_file_path = os.path.join(TEMP_FOLDER_PATH,request_file_name)
+            print("> Saving",request_file_name,"to",zip_file_path)
+
+            request_file = request_files.get(request_file_name)
+            request_file.save(zip_file_path)
+            
+            model_folder_name, _ = os.path.splitext(request_file_name)
+            model_folder_path = os.path.join(RVC_MODELS_PATH,model_folder_name)
+            
+            shutil.unpack_archive(zip_file_path, model_folder_path)
+
+            print("> Cleaning up model folder",model_folder_path)
+
+            print("> Moving file to model root folder")
+            # Move all files to model root folder
+            for root, dirs, files in os.walk(model_folder_path):
+                for file in files:
+                    file_path = os.path.join(root,file)
+                    if not os.path.isdir(file_path):
+                        # move file from nested folder into the base folder
+                        shutil.move(file_path,os.path.join(model_folder_path,file))
+
+            print("> Deleting model subfolders")
+            # Remove all subfolder
+            for root, dirs, files in os.walk(model_folder_path):
+                for dir in dirs:
+                    folder_path = os.path.join(root,dir)
+                    if os.path.isdir(folder_path):
+                        os.rmdir(folder_path)
+
+            print("> Success")
+    
+        response = json.dumps({"status":"ok"})
+        return response
+
+    except Exception as e:
+        print(e)
+        abort(500, DEBUG_PREFIX + " Exception occurs while uploading models.")
+
 def rvc_process_audio():
     """
     Process request audio file with the loaded RVC model

requirements-rvc.txt

@@ -8,3 +8,4 @@ bitarray==2.8.1
 sacrebleu==2.3.1
 numpy==1.23.0
 ffmpeg-python==0.2.0
+py7zr==0.20.6

server.py

@@ -91,6 +91,7 @@ parser.add_argument("--talkinghead-gpu", action="store_true", help="Run the talk
 parser.add_argument("--coqui-gpu", action="store_true", help="Run the voice models on the GPU (CPU is default)")
 parser.add_argument("--coqui-models", help="Install given Coqui-api TTS model at launch (comma separated list, last one will be loaded at start)")
 
+parser.add_argument("--max-content-length", help="Set the max")
 parser.add_argument("--rvc-save-file", action="store_true", help="Save the last rvc input/output audio file into data/tmp/ folder (for research)")
 
 parser.add_argument("--stt-vosk-model-path", help="Load a custom vosk speech-to-text model")
@@ -327,6 +328,15 @@ CORS(app)  # allow cross-domain requests
 Compress(app) # compress responses
 app.config["MAX_CONTENT_LENGTH"] = 100 * 1024 * 1024
 
+max_content_length = (
+    args.max_content_length
+    if args.max_content_length
+    else None)
+
+if max_content_length is not None:
+    print("Setting MAX_CONTENT_LENGTH to",max_content_length,"Mb")
+    app.config["MAX_CONTENT_LENGTH"] = int(max_content_length) * 1024 * 1024
+
 if "vosk-stt" in modules:
     print("Initializing Vosk speech-recognition (from ST request file)")
     vosk_model_path = (
@@ -365,6 +375,7 @@ if "streaming-stt" in modules:
 
 if "rvc" in modules:
     print("Initializing RVC voice conversion (from ST request file)")
+    print("Increasing server upload limit")
     rvc_save_file = (
     args.rvc_save_file
     if args.rvc_save_file
@@ -380,8 +391,10 @@ if "rvc" in modules:
     rvc_module.save_file = rvc_save_file
     rvc_module.fix_model_install()
     app.add_url_rule("/api/voice-conversion/rvc/get-models-list", view_func=rvc_module.rvc_get_models_list, methods=["POST"])
+    app.add_url_rule("/api/voice-conversion/rvc/upload-models", view_func=rvc_module.rvc_upload_models, methods=["POST"])
     app.add_url_rule("/api/voice-conversion/rvc/process-audio", view_func=rvc_module.rvc_process_audio, methods=["POST"])
 
+
 if "coqui-tts" in modules:
     mode = "GPU" if args.coqui_gpu else "CPU"
     print("Initializing Coqui TTS client in " + mode + " mode")