from transformers import pipeline
import torch
import gradio as gr

device = "cuda:0" if torch.cuda.is_available() else "cpu"

pipe = pipeline(
    "automatic-speech-recognition",
    model="openai/whisper-small.en",
    chunk_length_s=30,
    device=device,
)

# Function to transcribe audio
def transcribe(audio):
    text = pipe(audio)["text"]
    return text

# Create the interface
with gr.Blocks() as demo:
    with gr.Row():
      with gr.Column(scale=1):  
        audio_input = gr.Audio(sources=["microphone"], type="filepath", label="Record Audio")
        submit_button = gr.Button("Transcribe")
        text_output = gr.Textbox(label="Transcription")

    submit_button.click(fn=transcribe, inputs=audio_input, outputs=text_output)


demo.launch(share=True)