Update app.py

app.py

@@ -1,26 +1,14 @@
 import gradio as gr
+from huggingface_hub import InferenceClient
 from transformers import pipeline
 from gtts import gTTS
 import io
 import tempfile
-import speech_recognition as sr
-recognizer = sr.Recognizer()
-
-def speech_to_text(audio_in):
-    with sr.AudioFile(audio_in) as source:
-        audio = recognizer.record(source)
-        try:
-            text = recognizer.recognize_google(audio)
-            return text
-        except Exception as e:
-            return "Sorry, I could not understand the audio :("
-        except Exception as e:
-            return "Sorry, my speech service is down :("
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-#client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 modelpath = "distilgpt2"
 
@@ -51,24 +39,44 @@ def continue_conversation(new_message):
 #new_message = "Sure, I can help with that. Could you please provide me with some details about the loan you need?"
 #continue_conversation(new_message)
 
-def converse(audio_in, system_message, max_tokens, temperature, top_p):
-    input_transcript = speech_to_text(inputsf)
-    if input_transcript.startswith("Sorry"):
-        return input_transcript
-    else:
-        history = []
-        llm_out = pipe(input_transcript, max_length=256, num_return_sequences=1)
-    print(llm_out)        
-    return llm_out
-        
+def respond(
+    message,
+    history: list[tuple[str, str]],
+    system_message,
+    max_tokens,
+    temperature,
+    top_p,
+):
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
+
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+
+        response += token
+        yield response
+
+
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
-demo = gr.Interface(
-    fn=converse,
-    inputs=[
-        gr.Microphone(label="Speak now...", type="numpy"),
-    ],
+demo = gr.ChatInterface(
+    respond,
     additional_inputs=[
         gr.Textbox(value="You are a Roleplaying Customer to a Housing Finance and Loans Company. DONOT say anything that sounds like an AI. Generate text like a natural human would.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
@@ -81,7 +89,6 @@ demo = gr.Interface(
             label="Top-p (nucleus sampling)",
         ),
     ],
-    outputs="text",
 )