Update app.py

app.py

@@ -77,7 +77,7 @@ llm_model = os.environ.get("LLM_MODEL", "mistral") # or "zephyr"
 
 title = f"Voice chat with {llm_model.capitalize()} and Coqui XTTS"
 
-DESCRIPTION = f"""# Voice chat with {llm_model.capitalize()} and Coqui XTTS"""
+DESCRIPTION = f"""# Voice/text chat with Vikk AI"""
 css = """.toast-wrap { display: none !important } """
 
 from huggingface_hub import HfApi
@@ -143,7 +143,7 @@ else:
 from llama_cpp import Llama
 # set GPU_LAYERS to 15 if you have a 8GB GPU so both models can fit in
 # else 35 full layers + XTTS works fine on T4 16GB
-GPU_LAYERS=int(os.environ.get("GPU_LAYERS", 15))
+GPU_LAYERS=int(os.environ.get("GPU_LAYERS", 35))
 
 LLAMA_VERBOSE=False
 print("Running LLM")
@@ -689,21 +689,21 @@ latent_map["AI Assistant"] = get_latents("examples/female.wav")
 
 #### GRADIO INTERFACE ####
 EXAMPLES = [
-    [[],"What is 42?"],
-    [[],"Speak in French, tell me how are you doing?"],
-    [[],"Antworten Sie mir von nun an auf Deutsch"],
+    [[],"What are my rights if I've been arrested?"],
+    [[],"What should I do if I've been injured in an accident due to someone else's negligence?"],
+    [[],"How can I protect my assets and plan for the future through estate planning?"],
     
 ]
 
-
-OTHER_HTML=f"""<div>
-<a style="display:inline-block" href='https://github.com/coqui-ai/TTS'><img src='https://img.shields.io/github/stars/coqui-ai/TTS?style=social' /></a>
-<a style='display:inline-block' href='https://discord.gg/5eXr5seRrv'><img src='https://discord.com/api/guilds/1037326658807533628/widget.png?style=shield' /></a>
-<a href="https://huggingface.co/spaces/coqui/voice-chat-with-mistral?duplicate=true">
-<img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
-<img referrerpolicy="no-referrer-when-downgrade" src="https://static.scarf.sh/a.png?x-pxid=0d00920c-8cc9-4bf3-90f2-a615797e5f59" />
-</div>
-"""
+OTHER_HTML= ''
+# OTHER_HTML=f"""<div>
+# <a style="display:inline-block" href='https://github.com/coqui-ai/TTS'><img src='https://img.shields.io/github/stars/coqui-ai/TTS?style=social' /></a>
+# <a style='display:inline-block' href='https://discord.gg/5eXr5seRrv'><img src='https://discord.com/api/guilds/1037326658807533628/widget.png?style=shield' /></a>
+# <a href="https://huggingface.co/spaces/coqui/voice-chat-with-mistral?duplicate=true">
+# <img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
+# <img referrerpolicy="no-referrer-when-downgrade" src="https://static.scarf.sh/a.png?x-pxid=0d00920c-8cc9-4bf3-90f2-a615797e5f59" />
+# </div>
+# """
 with gr.Blocks(title=title) as demo:
     gr.Markdown(DESCRIPTION)
     gr.Markdown(OTHER_HTML)
@@ -780,17 +780,17 @@ with gr.Blocks(title=title) as demo:
 
     file_msg.then(lambda: (gr.update(interactive=True),gr.update(interactive=True,value=None)), None, [txt, btn], queue=False)
 
-    gr.Markdown(
-        """
-This Space demonstrates how to speak to a chatbot, based solely on open-source models.
-It relies on 3 stage models:
-- Speech to Text : [Whisper-large-v2](https://sanchit-gandhi-whisper-large-v2.hf.space/) as an ASR model, to transcribe recorded audio to text. It is called through a [gradio client](https://www.gradio.app/docs/client).
-- LLM Model      : [Mistral-7b-instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) as the chat model, GGUF Q5_K_M quantized version used locally via llama_cpp[huggingface_hub](TheBloke/Mistral-7B-Instruct-v0.1-GGUF).
-- Text to Speech : [Coqui's XTTS](https://huggingface.co/spaces/coqui/xtts) as a Multilingual TTS model, to generate the chatbot answers. This time, the model is hosted locally.
-Note:
-- By using this demo you agree to the terms of the Coqui Public Model License at https://coqui.ai/cpml
-- Responses generated by chat model should not be assumed correct or taken serious, as this is a demonstration example only
-- iOS (Iphone/Ipad) devices may not experience voice due to autoplay being disabled on these devices by Vendor"""
-    )
+#     gr.Markdown(
+#         """
+# This Space demonstrates how to speak to a chatbot, based solely on open-source models.
+# It relies on 3 stage models:
+# - Speech to Text : [Whisper-large-v2](https://sanchit-gandhi-whisper-large-v2.hf.space/) as an ASR model, to transcribe recorded audio to text. It is called through a [gradio client](https://www.gradio.app/docs/client).
+# - LLM Model      : [Mistral-7b-instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) as the chat model, GGUF Q5_K_M quantized version used locally via llama_cpp[huggingface_hub](TheBloke/Mistral-7B-Instruct-v0.1-GGUF).
+# - Text to Speech : [Coqui's XTTS](https://huggingface.co/spaces/coqui/xtts) as a Multilingual TTS model, to generate the chatbot answers. This time, the model is hosted locally.
+# Note:
+# - By using this demo you agree to the terms of the Coqui Public Model License at https://coqui.ai/cpml
+# - Responses generated by chat model should not be assumed correct or taken serious, as this is a demonstration example only
+# - iOS (Iphone/Ipad) devices may not experience voice due to autoplay being disabled on these devices by Vendor"""
+#     )
 demo.queue()
 demo.launch(debug=True)