Update app.py

app.py

@@ -18,9 +18,6 @@ seg = pipeline("image-segmentation", model="facebook/mask2former-swin-base-coco-
 sd_pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
 sd_pipe = sd_pipe.to("cuda" if torch.cuda.is_available() else "cpu")
 
-# --- Speech ---
-asr = pipeline("automatic-speech-recognition", model="openai/whisper-small")
-tts = pipeline("text-to-speech", model="espnet/kan-bayashi_ljspeech_vits")
 
 # --- Functions ---
 def classify_text(text):
@@ -48,12 +45,7 @@ def generate_image(prompt):
     image = sd_pipe(prompt).images[0]
     return image
 
-def transcribe(audio):
-    return asr(audio)["text"]
 
-def speak_text(text):
-    audio = tts(text)
-    return (audio["sample_rate"], audio["audio"])
 
 # --- Gradio Interface ---
 with gr.Blocks() as demo:
@@ -100,14 +92,5 @@ with gr.Blocks() as demo:
         gen_out = gr.Image(label="Generated Image")
         gr.Button("Generate").click(generate_image, gen_in, gen_out)
 
-    with gr.Tab("Speech Recognition"):
-        audio_in = gr.Audio(type="filepath")
-        audio_out = gr.Textbox(label="Transcription")
-        audio_in.change(transcribe, audio_in, audio_out)
-
-    with gr.Tab("Text-to-Speech"):
-        tts_in = gr.Textbox(label="Text to Speak")
-        tts_out = gr.Audio(label="Generated Speech")
-        gr.Button("Speak").click(speak_text, tts_in, tts_out)
 
 demo.launch()