Update app.py

app.py

@@ -31,12 +31,23 @@ import torch
 import torchaudio
 from speechbrain.pretrained import SpectralMaskEnhancement
 
+import whisper
+model = whisper.load_model("small")
+
+import openai
+
 enhance_model = SpectralMaskEnhancement.from_hparams(
 source="speechbrain/metricgan-plus-voicebank",
 savedir="pretrained_models/metricgan-plus-voicebank",
 run_opts={"device":"cuda"},
 )
 
+mes = [
+    {"role": "system", "content": "You are my personal assistant. Try to be helpful."}
+]
+
+res = []
+
 from TTS.tts.utils.synthesis import synthesis
 from TTS.tts.utils.text.symbols import make_symbols, phonemes, symbols
 try:
@@ -114,8 +125,43 @@ def compute_spec(ref_file):
   
 
     
-def greet(Text,Voicetoclone,VoiceMicrophone):
-    text= "%s" % (Text)
+def greet(Text, audio, Voicetoclone,VoiceMicrophone):
+    
+    openai.api_key = Text
+
+    # 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)
+    res.append(result.text)
+
+    messages = mes
+
+    # chatgpt
+    n = len(res)
+    content = res[n-1]
+    messages.append({"role": "user", "content": content})
+
+    completion = openai.ChatCompletion.create(
+      model = "gpt-3.5-turbo",
+      messages = messages
+    )
+
+    chat_response = completion.choices[0].message.content
+
+    messages.append({"role": "assistant", "content": chat_response})   
+    
+    text= "%s" % (chat_response)
     if Voicetoclone is not None:
       reference_files= "%s" % (Voicetoclone)
       print("path url")
@@ -181,7 +227,7 @@ def greet(Text,Voicetoclone,VoiceMicrophone):
 
 demo = gr.Interface(
     fn=greet, 
-    inputs=[gr.inputs.Textbox(label='What would you like the voice to say? (max. 2000 characters per request)'),gr.Audio(type="filepath",         source="upload",label='Please upload a voice to clone (max. 30mb)'),gr.Audio(source="microphone", type="filepath", streaming=True)],
+    inputs=[gr.inputs.Textbox(label='请输入您的openai.api_key'),gr.Audio(type="filepath", source="upload",label='Please upload a voice to clone (max. 30mb)'),gr.Audio(source="microphone", type="filepath", streaming=True)],
     outputs="audio",
     title="Bilal's Voice Cloning Tool"
     )