Update app.py

app.py

@@ -1,66 +1,13 @@
 import time
-import os
-os.system("pip install git+https://github.com/openai/whisper.git")
 import gradio as gr
-import whisper
 import config as cfg
 import openai
-# import speech_recognition as sr
 from gtts import gTTS
-from gradio_client import Client
-# import numpy as np
 
-model = whisper.load_model("small")
 
 
         
-def transcribe_file(audio):
-    audio = whisper.load_audio(audio)
-    audio = whisper.pad_or_trim(audio)
-    
-    mel = whisper.log_mel_spectrogram(audio).to(model.device)
-    
-    _, probs = model.detect_language(mel)
-    
-    options = whisper.DecodingOptions(fp16 = False)
-    result = whisper.decode(model, mel, options)
-    
-    # print(result.text)
-    return result.text
-
-
-# openai.api_key = 'Your Key and Uncomment'
-# r = sr.Recognizer()
-
-# WHISPER_TIMEOUT = int(os.environ.get("WHISPER_TIMEOUT", 45))
 
-# whisper_client = Client("https://sanchit-gandhi-whisper-large-v2.hf.space/")
-
-# def transcribe_file(wav_path):
-#     try:
-#         # get result from whisper and strip it to delete begin and end space
-#         return whisper_client.predict(
-# 				wav_path,	# str (filepath or URL to file) in 'inputs' Audio component
-# 				"transcribe",	# str in 'Task' Radio component
-# 				api_name="/predict"
-#         ).strip()
-#     except:
-#         gr.Warning("There was a problem with Whisper endpoint, telling a joke for you.")
-#         return "There was a problem with my voice, tell me joke"
-    
-
-# def transcribe_file(speech_file):
-#     """Transcribe the audio file."""
-#     text = ""
-#     speech = np.array(speech_file,dtype=np.float32)
-#     audio_data = sr.AudioData(speech.tobytes(), 44100)
-#     with sr.AudioFile(audio_data) as audio_file:
-#         content = r.record(audio_file)
-    
-#     content = r.recognize_google(content)
-    
-#     text +=content
-#     return text
 
 def add_user_input(history, text):
     """Add user input to chat hostory."""
@@ -104,24 +51,16 @@ with gr.Blocks() as bot_interface:
             )
         with gr.Column(min_width=70, scale=1):
             submitBtn = gr.Button("Send")
-    with gr.Row():
-        audio_input= gr.Audio(
-                    label="Input Audio",
-                    show_label=False,
-                    sources="microphone",
-                    type="filepath"
-                )
+   
     with gr.Row():
         output = gr.Audio(speak,visible=True,autoplay=True)
-        speakBtn = gr.Button("Speak")
+        speakBtn = gr.Button("Listen")
 
 
     
     input_msg = user_input.submit(add_user_input, [chatbot, user_input], [chatbot, user_input], queue=False).then(bot_response, chatbot, chatbot)
     submitBtn.click(add_user_input, [chatbot, user_input], [chatbot, user_input], queue=False).then(bot_response, chatbot, chatbot)
     input_msg.then(lambda: gr.update(interactive=True), None, [user_input], queue=False)
-    inputs_event = audio_input.stop_recording(transcribe_file,inputs=[audio_input], outputs=[user_input],api_name="predict").then(add_user_input, [chatbot, user_input], [chatbot, user_input], queue=False).then(bot_response, chatbot, chatbot)
-    # inputs_event.then(lambda: gr.update(interactive=False), None, [user_input], queue=False)
     speakBtn.click(fn = speak,outputs=output)
 bot_interface.title = cfg.bot["title"]
 bot_interface.launch(share=True)