Update README.md

README.md

@@ -64,10 +64,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
 
 text = """
-The Mayor informed that a proposal from the company Águas do Vale was received 
-for the maintenance of the parish's wastewater systems. 
-The proposal will be reviewed by the technical department 
-and submitted to voting in the next meeting.
+17. PROCESSO DE OBRAS N.º ***** -- EDIFIC\nPelo Senhor Presidente foi presente a esta reunião a informação n.º ****** da Secção de Urbanismo e Fiscalização -- Serviço de Obras Particulares que se anexa à presente ata. \nPonderado e analisado o assunto o Executivo Municipal deliberou por unanimidade aprovar as especialidades relativas ao processo de obras n.º ***** -- EDIFIC.
 """
 
 inputs = tokenizer(text, return_tensors="pt", max_length=1024, truncation=True)
@@ -79,7 +76,7 @@ print(tokenizer.decode(summary_ids[0], skip_special_tokens=True))
 # 🧾 Model Output
 
 **Output:**  
-> "Proposal from Águas do Vale for wastewater maintenance will be reviewed and voted on in the next meeting."
+> "O Executivo Municipal aprovou, por unanimidade, as especialidades relativas a um processo de obras particulares."
 
 ---
 
@@ -116,15 +113,13 @@ print(tokenizer.decode(summary_ids[0], skip_special_tokens=True))
 
 The model was trained on a specialized dataset of **Portuguese municipal meeting minutes**, consisting of:
 
-- Discussion transcripts from official council sessions  
+- Discussion Subjects from official municipal meeting minutes.  
 - Decisions and deliberations across departments (urban planning, finance, education, etc.)  
 - Expert-annotated summaries per discussion segment  
 
 **Dataset sources include:**
 
-- Municipal chambers’ public records  
-- City council meeting archives  
-- Edited and standardized text from transcribed minutes  
+- Six Portuguese municipalities meeting minutes
 
 ---