baidu-ai-search

{ "cells": [ { "cell_type": "markdown", "metadata": { "collapsed": true, "pycharm": { "name": "#%% md\n" } }, "source": [ "# 短语音识别组件\n", "\n", "## 目标\n", "使用短语音识别组件对输入的语音文件进行识别，返回识别的文字。\n", "\n", "## 准备工作\n", "### 平台注册\n", "1.先在appbuilder平台注册，获取token\n", "\n", "2.安装appbuilder-sdk" ] }, { "cell_type": "code", "execution_count": null, "outputs": [], "source": [ "!pip install appbuilder-sdk" ], "metadata": { "collapsed": false, "pycharm": { "name": "#%%\n" } } }, { "cell_type": "markdown", "source": [ "## 基本用法\n", "\n", "### 快速开始\n", "\n", "下面是短语音识别的代码示例：" ], "metadata": { "collapsed": false } }, { "cell_type": "code", "execution_count": null, "outputs": [], "source": [ "import os\n", "import requests\n", "import appbuilder\n", "# 设置环境变量和初始化\n", "# 请前往千帆AppBuilder官网创建密钥，流程详见：https://cloud.baidu.com/doc/AppBuilder/s/Olq6grrt6#1%E3%80%81%E5%88%9B%E5%BB%BA%E5%AF%86%E9%92%A5\n", "os.environ[\"APPBUILDER_TOKEN\"] = \"...\"\n", "\n", "asr = appbuilder.ASR()\n", "\n", "audio_file_url = \"https://bj.bcebos.com/v1/appbuilder/asr_test.pcm?authorization=bce-auth-v1\" \\\n", " \"%2FALTAKGa8m4qCUasgoljdEDAzLm%2F2024-01-11T10%3A56%3A41Z%2F-1%2Fhost\" \\\n", " \"%2Fa6c4d2ca8a3f0259f4cae8ae3fa98a9f75afde1a063eaec04847c99ab7d1e411\"\n", "audio_data = requests.get(audio_file_url).content\n", "content_data = {\"audio_format\": \"pcm\", \"raw_audio\": audio_data, \"rate\": 16000}\n", "msg = appbuilder.Message(content_data)\n", "out = asr.run(msg)\n", "print(out.content)" ], "metadata": { "collapsed": false, "pycharm": { "name": "#%%\n" } } }, { "cell_type": "markdown", "source": [ "## 参数说明\n", "\n", "### 鉴权配置\n", "使用组件之前，请首先申请并设置鉴权参数，可参考[组件使用流程](https://cloud.baidu.com/doc/AppBuilder/s/Olq6grrt6#1%E3%80%81%E5%88%9B%E5%BB%BA%E5%AF%86%E9%92%A5)。\n", "```python\n", "# 设置环境中的TOKEN，以下示例略\n", "os.environ[\"APPBUILDER_TOKEN\"] = \"bce-YOURTOKEN\"\n", "```\n", "\n", "### 初始化参数\n", "\n", "无\n", "\n", "### 调用参数\n", "\n", "|参数名称 |参数类型 |是否必须 |描述 | 示例值 |\n", "|--------|--------|--------|----|--------|\n", "|message |String |是 |输入的消息，用于模型的主要输入内容。这是一个必需的参数| Message(content={\"raw_audio\": b\"...\"}) |\n", "|audio_format|String|是 |定义语言文件的格式，包括\"pcm\"、\"wav\"、\"amr\"、\"m4a\"，默认值为\"pcm\"| pcm |\n", "|rate|Integer|是 |定义录音采样率，固定值16000| 16000 |\n", "|timeout| Float | 否 | HTTP超时时间,单位：秒 |1|\n", "|retry|Integer|是 |HTTP重试次数| 3 |\n", "\n", "### 响应参数\n", "|参数名称 | 参数类型 |描述 |示例值|\n", "|--------|--------------|----|------|\n", "|result | List[String] |返回结果|[\"北京科技馆。\"]|\n", "\n", "### 响应示例\n", "```json\n", "{\"result\": [\"北京科技馆。\"]}\n", "```\n", "### 错误码\n", "| 错误码 |描述|\n", "|---|---|\n", "| 0 |success|\n", "| 2000 |data empty|" ], "metadata": { "collapsed": false, "pycharm": { "name": "#%% md\n" } } } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 2 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython2", "version": "2.7.6" } }, "nbformat": 4, "nbformat_minor": 0 }