Update app.py

app.py

@@ -1,15 +1,14 @@
-import whisper
-import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import gradio as gr
-# from gradio import inputs  # Import the 'inputs' module from 'gradio'
 
 
 
-Asr_model = whisper.load_model("base")
-Asr_model.device
+
+
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import gradio as gr
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
+
 model_name = "ai4bharat/Airavata"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name, padding_side="left")
@@ -53,43 +52,10 @@ def inference(input_prompt, model, tokenizer):
     return output_text
 
 
-def transcribe(audio):
-    
-    #time.sleep(3)
-    # load audio and pad/trim it to fit 30 seconds
-    audio = whisper.load_audio(audio)
-    audio = whisper.pad_or_trim(audio)
-
-    # make log-Mel spectrogram and move to the same device as the model
-    mel = whisper.log_mel_spectrogram(audio).to(model.device)
-
-    # detect the spoken language
-    _, probs = model.detect_language(mel)
-    print(f"Detected language: {max(probs, key=probs.get)}")
-
-    # decode the audio
-    options = whisper.DecodingOptions()
-    result = whisper.decode(model, mel, options)
-    return result.text
-
-
-def chat_interface(audio_tuple ):
-    audio_path = audio_tuple[0] if isinstance(audio_tuple, tuple) else audio_tuple
-
-    message = transcribe(audio_path)
+def chat_interface(message,history):
     outputs = inference(message, model, tokenizer)
     return outputs
 
 
-gr.Interface(
-    title="CAMAI - Centralized Actionable Multimodal Agri Assistant on Edge Intelligence for Farmers",
-    fn=chat_interface,
-    inputs=[
-        gr.Audio(sources=["microphone"])
-    ],
-
-    outputs=[
-        "textbox"
-    ],
-    theme="darkly"
-).launch()
+chat_interface = gr.ChatInterface(chat_interface, title="CAMAI")
+chat_interface.launch()