adapt for better working

app.py

@@ -1,25 +1,33 @@
 from transformers import pipeline
 import gradio as gr
 
-model_name_converter = {"bart_large":"juliosocher/bart-large-cnn-finetuned-scientific-articles",
-                        "mt5-small-finetuned-mt5":"jacks392/mt5-small-finetuned-mt5",
-                        "facebook": "facebook/bart-large-cnn",
-                        "google" : "google/pegasus-xsum"
-                        }
-def predict(prompt,model_name, max_length):
-    if model_name ==None:
-        model_name = "google/pegasus-xsum"
+
+MODELS = {
+    "gsarti": pipeline("summarization", model="gsarti/it5-base-wiki-summarization"),
+    "facebook": pipeline("summarization", model="facebook/bart-large-cnn"),
+    "lincoln": pipeline(
+        "summarization", model="lincoln/mbart-mlsum-automatic-summarization"
+    ),
+    "google": pipeline("summarization", model="google/pegasus-large"),
+    "t5-small": pipeline("summarization", model="t5-small"),
+}
+
+
+def predict(prompt, model_name, max_length):
+    if model_name is None:
+        model = MODELS["t5-small"]
     else:
-        model_name = model_name_converter[model_name]
-    model = pipeline("summarization",model = model_name)
-    summary = model(prompt,max_length)[0]["summary_text"]
+        model = MODELS[model_name]
+    prompt = prompt.replace("\n", " ")
+    summary = model(prompt, max_length)[0]["summary_text"]
     return summary
-        
-options_1 = list(model_name_converter.keys())
+
+
+options_1 = list(MODELS.keys())
 with gr.Blocks() as demo:
     drop_down = gr.Dropdown(choices=options_1, label="model")
-    textbox = gr.Textbox(placeholder = "Enter text block to summarize", lines = 4)
-    length=gr.Number(value = 200, label="the max number of characher for summerized")
-    gr.Interface(fn=predict, inputs=[textbox, drop_down, length], outputs = "text")
+    textbox = gr.Textbox(placeholder="Enter text block to summarize", lines=4)
+    length = gr.Number(value=100, label="the max number of characher for summerized")
+    gr.Interface(fn=predict, inputs=[textbox, drop_down, length], outputs="text")
 
 demo.launch()

requirements.txt

@@ -1,4 +1,5 @@
 gradio
 transformers
 tensorflow
-tf-keras
+tf-keras
+sentencepiece