from transformers import pipeline from moviepy.editor import * import gradio as gr import requests pipe = pipeline(model="kk90ujhun/whisper-small-hi") # change to "your-username/the-name-you-picked" def transcribe(my_video): # my_video = requests.get(my_url) # my_audio = my_video.audio # text = pipe(my_audio)["text"] # return text return type(my_video) iface = gr.Interface( fn=transcribe, inputs=gr.video(), outputs="text", title="Whisper Small Hindi", description="Realtime demo for Hindi speech recognition using a fine-tuned Whisper small model.", ) iface.launch()