from transformers_js_py import import_transformers_js, read_audio import gradio as gr transformers = await import_transformers_js() pipeline = transformers.pipeline pipe = await pipeline('automatic-speech-recognition', 'Xenova/whisper-tiny.en') async def asr(audio_path): audio = read_audio(audio_path, 16000) result = await pipe(audio) return result["text"] demo = gr.Interface( asr, gr.Audio(type="filepath"), gr.Text(), examples=[ ["jfk.wav"], ] ) demo.launch() transformers_js_py numpy scipy