| import torch | |
| import gradio as gr | |
| from transformers import pipeline | |
| pipe = pipeline( | |
| "automatic-speech-recognition", | |
| model="openai/whisper-small" | |
| ) | |
| def transcribe(input_audio): | |
| # Perform speech recognition on the input audio | |
| transcription = asr_pipeline(input_audio)["text"] | |
| return transcription | |
| gradio_app = gr.Interface( | |
| fn=transcribe, | |
| inputs=gr.Audio(type="filepath", label="Record or Upload Audio"), | |
| outputs=gr.Textbox(label="Transcription"), | |
| title="Speech to Text Transcription with Whisper", | |
| ) | |
| if __name__ == "__main__": | |
| gradio_app.launch() | |