from transformers import pipeline | |
import gradio as gr | |
pipe = pipeline(model="SharatChandra/whisper-fine-banking-dataset") # change to "your-username/the-name-you-picked" | |
def transcribe(audio): | |
text = pipe(audio, generate_kwargs = {"task":"translate", "language":"english"})["text"] | |
return text | |
iface = gr.Interface( | |
fn=transcribe, | |
inputs=gr.Audio(type="filepath"), | |
outputs="text", | |
title="Whisper Medium Bank Domain", | |
description="Realtime demo for Banking Domain speech recognition using a fine-tuned Whisper medium model.", | |
) | |
iface.launch() |