app.py

# Import necessary libraries
import gradio as gr
import numpy as np

# Define the function to transcribe audio
def transcribe(audio):
    sr, y = audio
    
    # Convert to mono if stereo
    if y.ndim > 1:
        y = y.mean(axis=1)
        
    y = y.astype(np.float32)
    y /= np.max(np.abs(y))
    # Placeholder for the actual transcription logic
    return "Transcribed text: " + " ".join([str(i) for i in y[:10]])

# Create a Gradio interface for full-context ASR
demo_full_context = gr.Interface(
    transcribe,
    gr.Audio(sources="microphone"),
    "text",
)

# Define the function to transcribe streaming audio
def transcribe_stream(stream, new_chunk):
    sr, y = new_chunk
    
    # Convert to mono if stereo
    if y.ndim > 1:
        y = y.mean(axis=1)
        
    y = y.astype(np.float32)
    y /= np.max(np.abs(y))
    if stream is not None:
        stream = np.concatenate([stream, y])
    else:
        stream = y
    # Placeholder for the actual transcription logic
    return stream, "Transcribed text: " + " ".join([str(i) for i in stream[:10]])

# Create a Gradio interface for streaming ASR
demo_streaming = gr.Interface(
    transcribe_stream,
    ["state", gr.Audio(sources=["microphone"], streaming=True)],
    ["state", "text"],
    live=True,
)

# Launch the interfaces
if __name__ == "__main__":
    demo_full_context.launch(show_error=True)
    demo_streaming.launch()