transformers_js_py from transformers_js import import_transformers_js import gradio as gr import numpy as np transformers = await import_transformers_js() pipeline = transformers.pipeline pipe = await pipeline("automatic-speech-recognition",'Xenova/whisper-small') async def transcribe(audio): sr, y = audio y = y.astype(np.float32) y /= np.max(np.abs(y)) return pipe({"sampling_rate": sr, "raw": y})["text"] demo = gr.Interface( transcribe, gr.Audio(source="microphone"), "text", theme=gr.themes.Soft(),) demo.launch()