Spaces:
Running
Running
from transformers import WhisperTokenizer | |
tokenizer = WhisperTokenizer.from_pretrained("openai/whisper-small", language="marathi", task="transcribe") | |
from transformers import pipeline | |
import gradio as gr | |
import torch | |
pipe = pipeline(model="thak123/whisper-small-gom", | |
task="automatic-speech-recognition", tokenizer= tokenizer) # change to "your-username/the-name-you-picked" | |
pipe.model.config.forced_decoder_ids = ( | |
pipe.tokenizer.get_decoder_prompt_ids( | |
language="marathi", task="transcribe" | |
) | |
) | |
def transcribe(audio): | |
text = pipe(audio)["text"] | |
return text | |
iface = gr.Interface( | |
fn=transcribe, | |
inputs=gr.Audio(source="microphone", type="filepath"), | |
outputs="text", | |
title="Whisper Small Konkani", | |
description="Realtime demo for Konkani speech recognition using a fine-tuned Whisper small model.", | |
) | |
iface.launch() |