Final

app.py

@@ -13,6 +13,7 @@ from pydub import AudioSegment
 from transformers import AutoTokenizer, AutoFeatureExtractor, set_seed
 from huggingface_hub import InferenceClient
 from streamer import ParlerTTSStreamer
+import time
 
 
 device = "cuda:0" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
@@ -75,13 +76,12 @@ def generate_response(audio):
                                               "For example, 'Magic 8 Ball, should I get a dog?', 'A dog is ready for you but are you ready for the dog?'")},
                 {"role": "user", "content": f"Magic 8 Ball please answer this question -  {question}"}]
     
-    response = client.chat_completion(messages, max_tokens=64, seed=random.randint(1, 5000),
-    model="mistralai/Mistral-7B-Instruct-v0.3")
+    response = client.chat_completion(messages, max_tokens=64, seed=random.randint(1, 5000), model="mistralai/Mistral-7B-Instruct-v0.3")
     response = response.choices[0].message.content.replace("Magic 8 Ball", "")
     return response, None, None
 
 @spaces.GPU
-def generate_base(answer):
+def read_response(answer):
 
     play_steps_in_s = 2.0
     play_steps = int(frame_rate * play_steps_in_s)
@@ -104,31 +104,28 @@ def generate_base(answer):
     set_seed(SEED)
     thread = Thread(target=model.generate, kwargs=generation_kwargs)
     thread.start()
-
+    start = time.time()
     for new_audio in streamer:
-        print(f"Sample of length: {round(new_audio.shape[0] / sampling_rate, 2)} seconds")
+        print(f"Sample of length: {round(new_audio.shape[0] / sampling_rate, 2)} seconds after {time.time() - start} seconds")
         yield answer, numpy_to_mp3(new_audio, sampling_rate=sampling_rate)
 
-css=""".my-group {max-width: 600px !important; max-height: 600 !important;}
-                      .my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
-
 
 with gr.Blocks() as block:
     gr.HTML(
         f"""
         <h1 style='text-align: center;'> Magic 8 Ball 🎱 </h1>
+        <h3 style='text-align: center;'> Ask a question and receive wisdom </h3>
         <p style='text-align: center;'> Powered by <a href="https://github.com/huggingface/parler-tts"> Parler-TTS</a>
         """
     )
     with gr.Group():
         with gr.Row():
-            audio_out = gr.Audio(visible=True, streaming=True, autoplay=True)
-            answer = gr.Textbox(visible=True, label="Answer")
+            audio_out = gr.Audio(label="Spoken Answer", streaming=True, autoplay=True, loop=False)
+            answer = gr.Textbox(label="Answer")
             state = gr.State()
-            
         with gr.Row():
             audio_in = gr.Audio(label="Speak you question", sources="microphone", type="filepath")
 
-    audio_in.stop_recording(generate_response, audio_in, [state, answer, audio_out]).then(fn=generate_base, inputs=state, outputs=[answer, audio_out])
+    audio_in.stop_recording(generate_response, audio_in, [state, answer, audio_out]).then(fn=read_response, inputs=state, outputs=[answer, audio_out])
 
 block.launch()