Update app.py

app.py

@@ -9,7 +9,8 @@ import urllib.request
 import zipfile
 import gdown
 from argparse import ArgumentParser
-
+import requests
+import random
 os.system("aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d . -o hubert_base.pt")
 os.system("aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt -d . -o rmvpe.pt")
 # os.system("aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/sail-rvc/yoimiya-jp/resolve/main/model.pth -d ./weights/yoimiya -o yoimiya.pth")
@@ -19,7 +20,7 @@ os.system("aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://hugging
 # os.system("aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/sail-rvc/Eminem2333333/blob/main/model.pth -d ./weights/Eminem -o Eminem.pth")
 # os.system("aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/sail-rvc/hitzeed-ch/resolve/main/model.index -d ./weights/Eminem -o Eminem.index")
 os.system("aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/zhuowen999/yutou/resolve/main/yutou.index -d ./weights/yutou -o yutou.index")
-os.system("aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/zhuowen999/yutou/resolve/main/yutou.pth -d ./weights/yutou -o .pth")
+os.system("aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/zhuowen999/yutou/resolve/main/yutou.pth -d ./weights/yutou -o yutou.pth")
 
 BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 
@@ -65,6 +66,41 @@ if len(models) == 0:
     raise ValueError("No model found in `weights` folder")
 models.sort()
 
+def tts_new(text,path):
+    url = "https://www.text-to-speech.cn/getSpeek.php"
+
+    payload = {
+        "user_id": str(random.randint(120100,2000000)),
+        "language": "中文（普通话，简体）",
+        "voice": "zh-CN-XiaoxiaoMultilingualNeural",
+        "text": text,
+        "role": "0",
+        "style": "0",
+        "styledegree": "1",
+        "volume": "75",
+        "predict": "0",
+        "rate": "-8",
+        "pitch": "0",
+        "kbitrate": "audio-16khz-128kbitrate-mono-mp3",
+        "silence": "",
+        "yzm": "^\""
+    }
+    headers = {
+        "Referer": "https://www.text-to-speech.cn/",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36 Edg/124.0.0.0",
+        "accept": "*/*",
+        "accept-language": "zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6",
+        "content-type": "application/x-www-form-urlencoded; charset=UTF-8",
+        "origin": "https://www.text-to-speech.cn",
+        "referer": "https://www.text-to-speech.cn/"
+    }
+
+    response = requests.post(url, data=payload, headers=headers)
+    url=response.json()['download']
+    print(response.json())
+    mp3=requests.get(url)
+    with open(path, "wb") as f:
+        f.write(mp3.content)
 
 def model_data(model_name):
     # global n_spk, tgt_sr, net_g, vc, cpt, version, index_file
@@ -178,11 +214,12 @@ def tts(
             speed_str = f"+{speed}%"
         else:
             speed_str = f"{speed}%"
-        asyncio.run(
-            edge_tts.Communicate(
-                tts_text, "-".join(tts_voice.split("-")[:-1]), rate=speed_str
-            ).save(edge_output_filename)
-        )
+        # asyncio.run(
+        #     edge_tts.Communicate(
+        #         tts_text, "-".join(tts_voice.split("-")[:-1]), rate=speed_str
+        #     ).save(edge_output_filename)
+        # )
+        tts_new(tts_text,edge_output_filename)
         t1 = time.time()
         edge_time = t1 - t0
         audio, sr = librosa.load(edge_output_filename, sr=16000, mono=True)