11

app.py

@@ -1,4 +1,5 @@
 import os
+import requests
 import re
 from num2words import num2words
 import gradio as gr
@@ -28,8 +29,39 @@ nltk.download('punkt')
 DEMO_PATH = os.getenv("DEMO_PATH", "./demo")
 TMP_PATH = os.getenv("TMP_PATH", "./demo/temp")
 MODELS_PATH = os.getenv("MODELS_PATH", "./pretrained_models")
+os.makedirs(MODELS_PATH, exist_ok=True)
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
+# download wmencodec
+url = "https://huggingface.co/westbrook/SSR-Speech-English/resolve/main/wmencodec.th"
+filename = os.path.join(MODELS_PATH, "wmencodec.th")
+response = requests.get(url, stream=True)
+response.raise_for_status()
+with open(filename, "wb") as file:
+    for chunk in response.iter_content(chunk_size=8192):
+        file.write(chunk)
+print(f"File downloaded to: {filename}")
+
+# download english model
+url = "https://huggingface.co/westbrook/SSR-Speech-English/resolve/main/English.pth"
+filename = os.path.join(MODELS_PATH, "English.th")
+response = requests.get(url, stream=True)
+response.raise_for_status()
+with open(filename, "wb") as file:
+    for chunk in response.iter_content(chunk_size=8192):
+        file.write(chunk)
+print(f"File downloaded to: {filename}")
+
+# download mandarin model
+url = "https://huggingface.co/westbrook/SSR-Speech-Mandarin/resolve/main/Mandarin.pth"
+filename = os.path.join(MODELS_PATH, "Mandarin.pth")
+response = requests.get(url, stream=True)
+response.raise_for_status()
+with open(filename, "wb") as file:
+    for chunk in response.iter_content(chunk_size=8192):
+        file.write(chunk)
+print(f"File downloaded to: {filename}")
+
 def get_random_string():
     return "".join(str(uuid.uuid4()).split("-"))