import gradio as gr from transformers import pipeline # Load the Automatic Speech Recognition pipeline from Hugging Face asr = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3") def transcribe(audio): if audio is None: return "Please record or upload an audio file." # audio is a tuple: (sample_rate, numpy array) result = asr(audio)["text"] return result description = """ # Speech-to-Text Converter Record your voice or upload an audio file and get the transcription using Hugging Face's Whisper model. """ demo = gr.Interface( fn=transcribe, inputs=gr.Audio(source="microphone", type="numpy", label="Record or Upload Audio"), outputs=gr.Textbox(label="Transcribed Text"), title="Speech to Text App", description=description, allow_flagging="never", theme="default" ) if __name__ == "__main__": demo.launch()