text

app.py

@@ -1,70 +1,10 @@
 from huggingface_hub import InferenceClient
-from transformers import pipeline
 import gradio as gr
-import edge_tts
-import tempfile
-import os
-from streaming_stt_nemo import Model
-import torch
-import random
-
-# Initialize the inference client with your Hugging Face token
-client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.1")
-# Initialize the ASR pipeline
-asr = pipeline("automatic-speech-recognition", "facebook/wav2vec2-base-960h")
-
-def speech_to_text(speech):
-    """Converts speech to text using the ASR pipeline."""
-    # breakpoint()
-    return asr(speech)["text"]
-
-
-def classify_mood(input_string):
-    """Classifies the mood based on keywords in the input string."""
-    input_string = input_string.lower()
-    mood_words = {"happy", "sad", "instrumental", "party"}
-    for word in mood_words:
-        if word in input_string:
-            return word, True
-    return None, False
 
-def generate(
-    prompt, history, temperature=0.1, max_new_tokens=2048, top_p=0.8, repetition_penalty=1.0,
-):
-    temperature = float(temperature)
-    if temperature < 1e-2:
-        temperature = 1e-2
-    top_p = float(top_p)
-
-    generate_kwargs = dict(
-        temperature=temperature,
-        max_new_tokens=max_new_tokens,
-        top_p=top_p,
-        repetition_penalty=repetition_penalty,
-        do_sample=True,
-        seed=42,
-    )
-
-    formatted_prompt = format_prompt(prompt, history)
-
-    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-    output = ""
-
-    for response in stream:
-        output += response.token.text
-        mood, is_classified = classify_mood(output)
-        # Print the chatbot's response
-        if is_classified:
-            print("Chatbot:", mood.capitalize())
-            playlist_message = f"Playing {mood.capitalize()} playlist for you!"
-            output=playlist_message
-            return output               
-        # yield output
-    return output
+client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.1")
 
 def format_prompt(message, history):
-    """Formats the prompt including fixed instructions and conversation history."""
-    fixed_prompt = """
+    fixed_prompt= """
             You are a smart mood analyser, who determines user mood. Based on the user input, classify the mood of the user into one of the four moods {Happy, Sad, Instrumental, Party}. If you are finding it difficult to classify into one of these four moods, keep the conversation going on until we classify the user’s mood. Return a single-word reply from one of the options if you have classified. Suppose you classify a sentence as happy, then just respond with "happy".
 
             Note: Do not write anything else other than the classified mood if classified.
@@ -233,41 +173,66 @@ def format_prompt(message, history):
 
             User: Lets turn up the music and have some fun!
             LLM Response: Party
-"""  # Include your fixed prompt and instructions here
-    prompt = f"{fixed_prompt}"
+            """
+    prompt = f"<s>{fixed_prompt}"
     for user_prompt, bot_response in history:
-        prompt += f"\nUser: {user_prompt}\nLLM Response: {bot_response}"
+        prompt += f"\n User:{user_prompt}\n LLM Response:{bot_response}"
+
+    # Add the current message
     prompt += f"\nUser: {message}\nLLM Response:"
+#   breakpoint()
     return prompt
+def classify_mood(input_string):
+    input_string = input_string.lower()
+    mood_words = {"happy", "sad", "instrumental", "party"}
+    for word in mood_words:
+        if word in input_string:
+            return word, True
+    return None, False
+
+def generate(
+    prompt, history, temperature=0.1, max_new_tokens=2048, top_p=0.8, repetition_penalty=1.0,
+):
+    temperature = float(temperature)
+    if temperature < 1e-2:
+        temperature = 1e-2
+    top_p = float(top_p)
+
+    generate_kwargs = dict(
+        temperature=temperature,
+        max_new_tokens=max_new_tokens,
+        top_p=top_p,
+        repetition_penalty=repetition_penalty,
+        do_sample=True,
+        seed=42,
+    )
+
+    formatted_prompt = format_prompt(prompt, history)
+    breakpoint()
+
+    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    output = ""
+
+    for response in stream:
+        output += response.token.text
+        mood, is_classified = classify_mood(output)
+        # Print the chatbot's response
+        if is_classified:
+            print("Chatbot:", mood.capitalize())
+            playlist_message = f"Playing {mood.capitalize()} playlist for you!"
+            output=playlist_message
+            return output               
+        # yield output
+    return output
+
+
+
+demo = gr.ChatInterface (fn=generate, 
+                        title="Mood-Based Music Recommender",
+                        retry_btn=None,
+                        undo_btn=None,
+                        clear_btn=None,
+                        description="<span style='font-size: larger; font-weight: bold;'>Hi! I'm a music recommender app. What kind of music do you want to listen to, or how are you feeling today?</span>",
+                       )
 
-async def process_speech(speech_file):
-        """Processes speech input to text and then calls generate."""
-        text = speech_to_text(speech_file)
-        reply = generate(text, history="")
-        communicate = edge_tts.Communicate(reply)
-        with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp_file:
-            tmp_path = tmp_file.name
-            await communicate.save(tmp_path)
-        yield tmp_path
-DESCRIPTION = """ # <center><b>Mood-Based Music Recommender⚡</b></center>
-        ### <center>Hi! I'm a music recommender app.
-        ### <center>What kind of music do you want to listen to, or how are you feeling today?</center>
-        """
-# Gradio interface setup
-with gr.Blocks(css="style.css") as demo:    
-    gr.Markdown(DESCRIPTION)
-    with gr.Row():
-        input = gr.Audio(label="User", sources="microphone", type="filepath", waveform_options=False)
-        output = gr.Audio(label="AI", type="filepath",
-                        interactive=False,
-                        autoplay=True,
-                        elem_classes="audio")
-        gr.Interface(
-            batch=True,
-            max_batch_size=10, 
-            fn=process_speech, 
-            inputs=[input],
-            outputs=[output], live=True)  
-
-if __name__ == "__main__":
-    demo.queue(max_size=200).launch()
+demo.queue().launch()