from transformers import pipeline
import gradio as gr

pipe = pipeline(model="jbatista79/whisper-jrb-small-es")  # change to "your-username/the-name-you-picked"

def transcribe(audio):
    text = pipe(audio)["text"]
    return text
'''
iface = gr.Interface(
    fn=transcribe,
    # inputs=gr.Audio(source="microphone", type="filepath"),
    inputs=gr.Audio(sources=["microphone"], type="filepath"),
    outputs="text",
    title="Whisper Small Spanish - Español (ES)",
    description="Realtime proof-of-concept demo for Spanish speech recognition using a fine-tuned Whisper small model. Created by Josué R. Batista - 2024-01-14",
)
iface.launch(share=True)
'''
with gr.Blocks() as app:
    with gr.Row():
        with gr.Column(): 
            gr.Image(value="lion-face-outline-cut-hi-strategia-black-strategia01-300x77.png", width=300, show_label=False, show_download_button=False, show_share_button=False)  # Adjust width as needed
        with gr.Column():
            gr.Markdown("## Whisper Small Spanish - Español (ES)")
            gr.Markdown("Realtime proof-of-concept demo for Spanish speech recognition using a fine-tuned Whisper small model. Created by Josué R. Batista - 2024-01-14")
    with gr.Row():
        audio_input = gr.Audio(sources=["microphone"], type="filepath")
        output_text = gr.Textbox()
    gr.Button("Transcribe").click(fn=transcribe, inputs=audio_input, outputs=output_text)

#app.launch(share=True)
app.launch()