Update app.py

app.py

@@ -201,9 +201,9 @@ class GradioInference:
         progress(0.40, desc="Summarizing")
         
         # Perform summarization on the transcription
-        transcription_summary = self.summarizer(
-            results["text"], max_length=150, min_length=30, do_sample=False
-        )
+        # transcription_summary = self.summarizer(
+        #     results["text"], max_length=150, min_length=30, do_sample=False
+        # )
 
         ########################## PRUEBA CHATGPT #################################
         from langchain.chains.llm import LLMChain
@@ -211,10 +211,11 @@ class GradioInference:
         from langchain.chains.combine_documents.stuff import StuffDocumentsChain
         
         OPENAI_API_KEY = os.environ['OPENAI_API_KEY']
-        
+
+        text = results["text"]
         # Define prompt
         prompt_template = """Write a concise summary of the following:
-        "{results["text"]}"
+        "{text}"
         CONCISE SUMMARY:"""
         prompt = PromptTemplate.from_template(prompt_template)
         
@@ -224,7 +225,7 @@ class GradioInference:
         
         # Define StuffDocumentsChain
         stuff_chain = StuffDocumentsChain(
-            llm_chain=llm_chain, document_variable_name="text"
+            llm_chain=llm_chain, document_variable_name=text
         )
         
         docs = loader.load()
@@ -233,28 +234,28 @@ class GradioInference:
         ########################## FIN PRUEBA CHATGPT #################################
         
         #### Prueba
-        WHITESPACE_HANDLER = lambda k: re.sub('\s+', ' ', re.sub('\n+', ' ', k.strip()))
+        # WHITESPACE_HANDLER = lambda k: re.sub('\s+', ' ', re.sub('\n+', ' ', k.strip()))
         
-        input_ids_sum = self.tokenizer(
-            [WHITESPACE_HANDLER(results["text"])],
-            return_tensors="pt",
-            padding="max_length",
-            truncation=True,
-            max_length=512
-        )["input_ids"]
+        # input_ids_sum = self.tokenizer(
+        #     [WHITESPACE_HANDLER(results["text"])],
+        #     return_tensors="pt",
+        #     padding="max_length",
+        #     truncation=True,
+        #     max_length=512
+        # )["input_ids"]
         
-        output_ids_sum = self.model.generate(
-            input_ids=input_ids_sum,
-            max_length=130,
-            no_repeat_ngram_size=2,
-            num_beams=4
-        )[0]
+        # output_ids_sum = self.model.generate(
+        #     input_ids=input_ids_sum,
+        #     max_length=130,
+        #     no_repeat_ngram_size=2,
+        #     num_beams=4
+        # )[0]
         
-        summary = self.tokenizer.decode(
-            output_ids_sum,
-            skip_special_tokens=True,
-            clean_up_tokenization_spaces=False
-        )
+        # summary = self.tokenizer.decode(
+        #     output_ids_sum,
+        #     skip_special_tokens=True,
+        #     clean_up_tokenization_spaces=False
+        # )
         #### Fin prueba
 
         progress(0.50, desc="Extracting Keywords")