separate fastapi

server/MMVCServerSIO.py

@@ -1,11 +1,11 @@
-import sys, os, struct, argparse, shutil, base64, traceback
+import sys, os, struct, argparse, shutil, traceback, base64, struct
+import numpy as np
 import misc.log_control
 
 from dataclasses import dataclass
 from datetime import datetime
 from distutils.util import strtobool
 
-import numpy as np
 from scipy.io.wavfile import write, read
 
 sys.path.append("MMVC_Trainer")
@@ -41,13 +41,10 @@ from mods.ssl import create_self_signed_cert
 
 from voice_changer.VoiceChangerManager import VoiceChangerManager
 from sio.MMVC_SocketIOServer import MMVC_SocketIOServer
-@dataclass
-class ExApplicationInfo():
-    external_tensorboard_port: int
-
-
-exApplitionInfo = ExApplicationInfo(external_tensorboard_port=0)
+from restapi.MMVC_Rest_VoiceChanger import MMVC_Rest_VoiceChanger
+from restapi.MMVC_Rest_Hello import MMVC_Rest_Hello
 
+from pydantic import BaseModel
 
 class VoiceModel(BaseModel):
     gpu: int
@@ -57,6 +54,16 @@ class VoiceModel(BaseModel):
     prefixChunkSize: int
     buffer: str
 
+@dataclass
+class ExApplicationInfo():
+    external_tensorboard_port: int
+
+
+exApplitionInfo = ExApplicationInfo(external_tensorboard_port=0)
+
+
+
+
 def setupArgParser():
     parser = argparse.ArgumentParser()
     parser.add_argument("-t", type=str, default="MMVC",
@@ -146,17 +153,16 @@ if __name__ == thisFilename or args.colab == True:
     app_fastapi.mount(
         "/recorder", StaticFiles(directory="../frontend/dist", html=True), name="static")
 
-    # sio = socketio.AsyncServer(
-    #     async_mode='asgi',
-    #     cors_allowed_origins='*'
-    # )
-    voiceChangerManager = VoiceChangerManager.get_instance()
-    # namespace = MMVC_Namespace.get_instance(voiceChangerManager)
-    # sio.register_namespace(namespace)
-    sio = MMVC_SocketIOServer.get_instance(voiceChangerManager)
+    voiceChangerManager = VoiceChangerManager.get_instance()    
     if CONFIG and MODEL:
         voiceChangerManager.loadModel(CONFIG, MODEL)
-    # namespace.loadWhisperModel("base")
+    sio = MMVC_SocketIOServer.get_instance(voiceChangerManager)
+
+    restHello = MMVC_Rest_Hello()
+    app_fastapi.include_router(restHello.router)
+    restVoiceChanger = MMVC_Rest_VoiceChanger(voiceChangerManager)
+    app_fastapi.include_router(restVoiceChanger.router)
+
 
     app_socketio = socketio.ASGIApp(
         sio,
@@ -171,10 +177,6 @@ if __name__ == thisFilename or args.colab == True:
         }
     )
 
-    @app_fastapi.get("/api/hello")
-    async def index():
-        return {"result": "Index"}
-
     ############
     # File Uploder
     # ##########
@@ -233,8 +235,8 @@ if __name__ == thisFilename or args.colab == True:
     # Voice Changer
     # ##########
 
-    @app_fastapi.post("/test")
-    async def post_test(voice: VoiceModel):
+    @app_fastapi.post("/test2")
+    async def post_test2(voice: VoiceModel):
         try:
             # print("POST REQUEST PROCESSING....")
             gpu = voice.gpu
@@ -342,7 +344,7 @@ if __name__ == thisFilename or args.colab == True:
         return JSONResponse(content=json_compatible_item_data)
 
 if __name__ == '__mp_main__':
-    printMessage(f"PHASE2adasdfadfasd:{__name__}", level=2)
+    printMessage(f"PHASE2:{__name__}", level=2)
 
 if __name__ == '__main__':
     printMessage(f"PHASE1:{__name__}", level=2)

server/restapi/MMVC_Rest_Hello.py

@@ -0,0 +1,13 @@
+from fastapi import APIRouter
+from fastapi.encoders import jsonable_encoder
+from fastapi.responses import JSONResponse
+class MMVC_Rest_Hello:
+    def __init__(self):
+        self.router = APIRouter()
+        self.router.add_api_route("/api/hello", self.hello, methods=["GET"])
+
+    def hello(self):
+        return {"result": "Index"}
+
+
+

server/restapi/MMVC_Rest_VoiceChanger.py

@@ -0,0 +1,71 @@
+import base64, struct
+import numpy as np
+
+from fastapi import APIRouter
+from fastapi.encoders import jsonable_encoder
+from fastapi.responses import JSONResponse
+
+from voice_changer.VoiceChangerManager import VoiceChangerManager
+from pydantic import BaseModel
+import threading
+
+class VoiceModel(BaseModel):
+    gpu: int
+    srcId: int
+    dstId: int
+    timestamp: int
+    prefixChunkSize: int
+    buffer: str
+
+class MMVC_Rest_VoiceChanger:
+    def __init__(self, voiceChangerManager:VoiceChangerManager):
+        self.voiceChangerManager = voiceChangerManager
+        self.router = APIRouter()
+        self.router.add_api_route("/test", self.test, methods=["POST"])
+        self.tlock = threading.Lock()
+
+
+    def test(self, voice: VoiceModel):
+        try:
+            gpu = voice.gpu
+            srcId = voice.srcId
+            dstId = voice.dstId
+            timestamp = voice.timestamp
+            prefixChunkSize = voice.prefixChunkSize
+            buffer = voice.buffer
+            wav = base64.b64decode(buffer)
+
+            if wav == 0:
+                samplerate, data = read("dummy.wav")
+                unpackedData = data
+            else:
+                unpackedData = np.array(struct.unpack(
+                    '<%sh' % (len(wav) // struct.calcsize('<h')), wav))
+                # write("logs/received_data.wav", 24000,
+                #       unpackedData.astype(np.int16))
+
+            self.tlock.acquire()
+            changedVoice = self.voiceChangerManager.changeVoice(
+                gpu, srcId, dstId, timestamp, prefixChunkSize, unpackedData)
+            self.tlock.release()
+
+            changedVoiceBase64 = base64.b64encode(changedVoice).decode('utf-8')
+            data = {
+                "gpu": gpu,
+                "srcId": srcId,
+                "dstId": dstId,
+                "timestamp": timestamp,
+                "prefixChunkSize": prefixChunkSize,
+                "changedVoiceBase64": changedVoiceBase64
+            }
+
+            json_compatible_item_data = jsonable_encoder(data)
+            return JSONResponse(content=json_compatible_item_data)
+
+        except Exception as e:
+            print("REQUEST PROCESSING!!!! EXCEPTION!!!", e)
+            print(traceback.format_exc())
+            return str(e)
+
+
+

server/sio/MMVC_Namespace.py

@@ -4,7 +4,6 @@ import numpy as np
 import socketio
 from voice_changer.VoiceChangerManager import VoiceChangerManager
 
-
 class MMVC_Namespace(socketio.AsyncNamespace):
     def __init__(self, namespace:str, voiceChangerManager:VoiceChangerManager):
         super().__init__(namespace)

server/voice_changer/VoiceChanger.py

@@ -46,7 +46,6 @@ class VoiceChanger():
     def on_request(self, gpu, srcId, dstId, timestamp, prefixChunkSize, wav):
         unpackedData = wav
         convertSize = unpackedData.shape[0] + (prefixChunkSize * 512)
-
         try:
 
             audio = torch.FloatTensor(unpackedData.astype(np.float32))