fixes

app.py

@@ -29,6 +29,14 @@ import soundfile as sf
 
 from model import get_pretrained_model, language_to_models
 
+hint_filename = f"{uuid.uuid4()}.wav"
+os.system(
+    f"""
+wget https://huggingface.co/spaces/k2-fsa/text-to-speech/resolve/main/hint.wav
+mv -v hint.wav {hint_filename}
+"""
+)
+
 
 def MyPrint(s):
     now = datetime.now()
@@ -127,14 +135,14 @@ def build_html_output(s: str, style: str = "result_item_success"):
 
 
 def process(language: str, repo_id: str, text: str, sid: str, speed: float):
+    MyPrint(f"Input text {len(text)}: {text}. sid: {sid}, speed: {speed}")
     if len(text) > 1000:
         info = (
             "To ensure this space is responsive, please use short text for testing\n"
             + "You can run sherpa-onnx locally to process long texts."
         )
-        return "", build_html_output(info)
+        return hint_filename, build_html_output(info)
 
-    MyPrint(f"Input text: {text}. sid: {sid}, speed: {speed}")
     sid = int(sid)
     tts = get_pretrained_model(repo_id, speed)