app.py

import gradio as gr
from transformers import pipeline

# 加载 kotoba-whisper-v2.2
speech_recognition_pipeline = pipeline("automatic-speech-recognition", model="kotoba-tech/kotoba-whisper-v2.2")

def transcribe(audio):
    result = speech_recognition_pipeline(audio)
    return result['text']

# 创建 Gradio 接口
demo = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(sources="upload", type="filepath"),
    outputs="text",
    title="Japanese Speech Recognition"
)


demo.launch()