Update app.py

app.py

@@ -4,6 +4,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 import gradio as gr
 from snac import SNAC
 
+
 def redistribute_codes(row):
     """
     Convert a sequence of token codes into an audio waveform using SNAC.
@@ -42,9 +43,9 @@ def redistribute_codes(row):
 snac_model = SNAC.from_pretrained("hubertsiuzdak/snac_24khz").to("cuda")
 
 # Load the single-speaker language model
-tokenizer = AutoTokenizer.from_pretrained('prithivMLmods/Llama-3B-Mono-Jim')
+tokenizer = AutoTokenizer.from_pretrained('prithivMLmods/Llama-3B-Mono-Cooper')
 model = AutoModelForCausalLM.from_pretrained(
-    'prithivMLmods/Llama-3B-Mono-Jim', torch_dtype=torch.bfloat16
+    'prithivMLmods/Llama-3B-Mono-Cooper', torch_dtype=torch.bfloat16
 ).cuda()
 
 @spaces.GPU
@@ -52,7 +53,7 @@ def generate_audio(text, temperature, top_p, max_new_tokens):
     """
     Given input text, generate speech audio.
     """
-    speaker = "Jim"
+    speaker = "Cooper"
     prompt = f'<custom_token_3><|begin_of_text|>{speaker}: {text}<|eot_id|><custom_token_4><custom_token_5><custom_token_1>'
     input_ids = tokenizer(prompt, add_special_tokens=False, return_tensors='pt').to('cuda')
     
@@ -75,8 +76,8 @@ def generate_audio(text, temperature, top_p, max_new_tokens):
 
 # Gradio Interface
 with gr.Blocks() as demo:
-    gr.Markdown("# Llama-3B-Mono-Jim - Single Speaker Audio Generation")
-    gr.Markdown("Generate speech audio using the `prithivMLmods/Llama-3B-Mono-Jim` model.")
+    gr.Markdown("# Llama-3B-Mono-Cooper - Single Speaker Audio Generation")
+    gr.Markdown("Generate speech audio using the `prithivMLmods/Llama-3B-Mono-Cooper` model.")
     
     with gr.Row():
         text_input = gr.Textbox(lines=4, label="Input Text")
@@ -96,4 +97,4 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()