gradio/demo/streaming_wav2vec/run.ipynb

{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: streaming_wav2vec"]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio torch transformers "]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["from transformers import pipeline\n", "import gradio as gr\n", "import time\n", "\n", "p = pipeline(\"automatic-speech-recognition\")\n", "\n", "def transcribe(audio, state=\"\"):\n", "    time.sleep(2)\n", "    text = p(audio)[\"text\"]  # type: ignore\n", "    state += text + \" \"\n", "    return state, state\n", "\n", "demo = gr.Interface(\n", "    fn=transcribe,\n", "    inputs=[\n", "        gr.Audio(sources=[\"microphone\"], type=\"filepath\", streaming=True),\n", "        \"state\"\n", "    ],\n", "    outputs=[\n", "        \"textbox\",\n", "        \"state\"\n", "    ],\n", "    live=True\n", ")\n", "\n", "if __name__ == \"__main__\":\n", "    demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}