Update app.py

app.py

@@ -21,16 +21,16 @@ summarization_model_names = [
 
 # Placeholder for the summarizer pipeline, tokenizer, and maximum tokens
 summarizer = None
-tokenizer = None
+tokenizer_sum = None
 max_tokens = None
 
 
 # Function to load the selected model
 def load_summarization_model(model_name):
-    global summarizer, tokenizer, max_tokens
+    global summarizer, tokenizer_sum, max_tokens
     try:
         summarizer = pipeline("summarization", model=model_name, torch_dtype=torch.bfloat16)
-        tokenizer = AutoTokenizer.from_pretrained(model_name)
+        tokenizer_sum = AutoTokenizer.from_pretrained(model_name)
         config = AutoConfig.from_pretrained(model_name)
 
         if hasattr(config, 'max_position_embeddings'):
@@ -51,7 +51,7 @@ def summarize_text(input, min_length, max_length):
     if summarizer is None:
         return "No model loaded!"
 
-    input_tokens = tokenizer.encode(input, return_tensors="pt")
+    input_tokens = tokenizer_sum.encode(input, return_tensors="pt")
     num_tokens = input_tokens.shape[1]
     if num_tokens > max_tokens:
         return f"Error: The input text has {num_tokens} tokens, which exceeds the maximum allowed {max_tokens} tokens. Please enter shorter text."
@@ -79,11 +79,9 @@ tokenizer = M2M100Tokenizer.from_pretrained(pretrained_model, cache_dir=cache_di
 translation_model = M2M100ForConditionalGeneration.from_pretrained(
         pretrained_model, cache_dir=cache_dir)
 
-transcription = pipeline("automatic-speech-recognition", model= "openai/whisper-base")
-clasification = pipeline(
-    "audio-classification",
-    model="anton-l/xtreme_s_xlsr_300m_minds14",
-)
+#transcription = pipeline("automatic-speech-recognition", model= "openai/whisper-base")
+#clasification = pipeline("audio-classification",model="anton-l/xtreme_s_xlsr_300m_minds14",)
+
 def language_names(json_path):
     with open(json_path, 'r') as json_file:
         data = json.load(json_file)
@@ -97,13 +95,13 @@ def get_name(label):
     name = label2name[iso_3]
     return name
 
-def audio_a_text(audio):
-  text = transcription(audio)["text"]
-  return text
+#def audio_a_text(audio):
+ # text = transcription(audio)["text"]
+  #return text
 
-def text_to_sentimient(audio):
-    #text = transcription(audio)["text"]
-    return clasification(audio)
+#def text_to_sentimient(audio):
+ #   #text = transcription(audio)["text"]
+  #  return clasification(audio)
 
 lang_id = {
     "Afrikaans": "af",
@@ -229,6 +227,7 @@ with demo:
   text = gr.Textbox()
   #gr.Markdown("Speech analyzer")
   #audio = gr.Audio(type="filepath", label = "Upload a file")
+    
   model_dropdown = gr.Dropdown(choices = summarization_model_names, label="Choose a model", value="sshleifer/distilbart-cnn-12-6")
   load_message = gr.Textbox(label="Load Status", interactive=False) 
   b1 = gr.Button("Load Model")
@@ -249,6 +248,7 @@ with demo:
    #             inputs=[
     #                source_lang])
   #b1 = gr.Button("convert to text")
+    
   b3 = gr.Button("translate")
   b3.click(translation_text, inputs = [source_lang, target_lang, text0], outputs = text)
   #b1.click(audio_a_text, inputs=audio, outputs=text)