当前位置： 首页 > news >正文

树莓派 ubuntu20.04下 python调讯飞的语音API，语音识别和语音合成

news 2025/9/12 8:28:05

目录

    • 1.环境搭建
    • 2.去讯飞官网申请密钥
    • 3.语音识别（sst）
    • 4.语音合成（tts）
    • 5.USB声卡可能报错

1.环境搭建

#环境说明：(尽量在ubuntu下使用, 本次代码均在该环境下实现)
sudo apt-get install sox  # 安装语音播放软件
pip install websocket-client==1.7.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install pydub==0.25.1 -i https://pypi.tuna.tsinghua.edu.cn/simple

2.去讯飞官网申请密钥

https://www.xfyun.cn/
在这里插入图片描述

3.语音识别（sst）

语音转文字

#! /usr/bin/env python
# -*- coding:utf-8 -*-
'''
1.环境说明：(尽量在ubuntu下使用, 本次代码均在该环境下实现)
pip install websocket-client==1.7.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install pydub==0.25.1 -i https://pypi.tuna.tsinghua.edu.cn/simplepyaudio的安装（注意区分不同平台）windows pip install pyaudio -i https://pypi.tuna.tsinghua.edu.cn/simpleLinux   sudo apt install python3-pyaudiomac     brew install portaudiopip install pyaudio -i https://pypi.tuna.tsinghua.edu.cn/simple2.密钥说明：
每一个账号的用额只有500次数的请求，平时用足够使用了。
自行前往去注册：https://www.xfyun.cn/'''
import wave
import pyaudio
import websocket
import datetime
import hashlib
import base64
import hmac
import json
from urllib.parse import urlencode
import time
import ssl
from wsgiref.handlers import format_date_time
from datetime import datetime
from time import mktime
import _thread as threadSTATUS_FIRST_FRAME = 0  # 第一帧的标识
STATUS_CONTINUE_FRAME = 1  # 中间帧标识
STATUS_LAST_FRAME = 2  # 最后一帧的标识class Ws_Param(object):# 初始化def __init__(self, APPID, APIKey, APISecret, AudioFile):self.APPID = APPIDself.APIKey = APIKeyself.APISecret = APISecretself.AudioFile = AudioFile# 公共参数(common)self.CommonArgs = {"app_id": self.APPID}# 业务参数(business)，更多个性化参数可在官网查看self.BusinessArgs = {"domain": "iat", "language": "zh_cn", "accent": "mandarin", "vinfo":1,"vad_eos":10000}# 生成urldef create_url(self):url = 'wss://ws-api.xfyun.cn/v2/iat'# 生成RFC1123格式的时间戳now = datetime.now()date = format_date_time(mktime(now.timetuple()))# 拼接字符串signature_origin = "host: " + "ws-api.xfyun.cn" + "\n"signature_origin += "date: " + date + "\n"signature_origin += "GET " + "/v2/iat " + "HTTP/1.1"# 进行hmac-sha256进行加密signature_sha = hmac.new(self.APISecret.encode('utf-8'), signature_origin.encode('utf-8'),digestmod=hashlib.sha256).digest()signature_sha = base64.b64encode(signature_sha).decode(encoding='utf-8')authorization_origin = "api_key=\"%s\", algorithm=\"%s\", headers=\"%s\", signature=\"%s\"" % (self.APIKey, "hmac-sha256", "host date request-line", signature_sha)authorization = base64.b64encode(authorization_origin.encode('utf-8')).decode(encoding='utf-8')# 将请求的鉴权参数组合为字典v = {"authorization": authorization,"date": date,"host": "ws-api.xfyun.cn"}# 拼接鉴权参数，生成urlurl = url + '?' + urlencode(v)# print("date: ",date)# print("v: ",v)# 此处打印出建立连接时候的url,参考本demo的时候可取消上方打印的注释，比对相同参数时生成的url与自己代码生成的url是否一致# print('websocket url :', url)return url# 收到websocket消息的处理
def on_message(ws, message):try:code = json.loads(message)["code"]sid = json.loads(message)["sid"]if code != 0:errMsg = json.loads(message)["message"]print("sid:%s call error:%s code is:%s" % (sid, errMsg, code))else:data = json.loads(message)["data"]["result"]["ws"]# print(json.loads(message))result = ""for i in data:for w in i["cw"]:result += w["w"]print(result)# print(json.dumps(data, ensure_ascii=False))except Exception as e:print("receive msg,but parse exception:", e)def on_error(ws, error):passdef on_close(ws):print("### closed ###")def on_open(ws):def run(*args):frameSize = 8000  # 每一帧的音频大小intervel = 0.04  # 发送音频间隔(单位:s)status = STATUS_FIRST_FRAME with open(wsParam.AudioFile, "rb") as fp:while True:buf = fp.read(frameSize)# 文件结束if not buf:status = STATUS_LAST_FRAME# 第一帧处理# 发送第一帧音频，带business 参数# appid 必须带上，只需第一帧发送if status == STATUS_FIRST_FRAME:d = {"common": wsParam.CommonArgs,"business": wsParam.BusinessArgs,"data": {"status": 0, "format": "audio/L16;rate=16000","audio": str(base64.b64encode(buf), 'utf-8'),"encoding": "raw"}}d = json.dumps(d)ws.send(d)status = STATUS_CONTINUE_FRAME# 中间帧处理elif status == STATUS_CONTINUE_FRAME:d = {"data": {"status": 1, "format": "audio/L16;rate=16000","audio": str(base64.b64encode(buf), 'utf-8'),"encoding": "raw"}}ws.send(json.dumps(d))# 最后一帧处理elif status == STATUS_LAST_FRAME:d = {"data": {"status": 2, "format": "audio/L16;rate=16000","audio": str(base64.b64encode(buf), 'utf-8'),"encoding": "raw"}}ws.send(json.dumps(d))time.sleep(1)break# 模拟音频采样间隔time.sleep(intervel)ws.close()thread.start_new_thread(run, ())
def record(time):    #录音程序CHUNK = 1024FORMAT = pyaudio.paInt16CHANNELS = 1RATE = 16000RECORD_SECONDS =timeWAVE_OUTPUT_FILENAME = "./output.pcm"p = pyaudio.PyAudio()stream = p.open(format=FORMAT,channels=CHANNELS,rate=RATE,input=True,frames_per_buffer=CHUNK)print("* recording")frames = []for i in range(0,int(RATE / CHUNK * RECORD_SECONDS)):data = stream.read(CHUNK)frames.append(data)print("* done recording")stream.stop_stream()stream.close()p.terminate()wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')wf.setnchannels(CHANNELS)wf.setsampwidth(p.get_sample_size(FORMAT))wf.setframerate(RATE)wf.writeframes(b''.join(frames))wf.close()if __name__ == "__main__":record(5)time1 = datetime.now()# 这里改成自己的key秘钥， 每个人每天只有500的访问量。wsParam = Ws_Param(APPID='d69356bc', APIKey='c3f938a4da84f7449bd2f958d461e7e1',APISecret='ZjE4ZGE4ZGU4YzViZmFhNTI0ZmYyNTE0',AudioFile=r'./output.pcm')websocket.enableTrace(False)wsUrl = wsParam.create_url()ws = websocket.WebSocketApp(wsUrl, on_message=on_message, on_error=on_error, on_close=on_close)ws.on_open = on_openws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})time2 = datetime.now()

4.语音合成（tts）

文字转语音

#! /usr/bin/env python
# -*- coding:utf-8 -*-
'''
1.环境说明：(尽量在ubuntu下使用, 本次代码均在该环境下实现)
pip install websocket-client==1.7.0 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install pydub==0.25.1 -i https://pypi.tuna.tsinghua.edu.cn/simple
pip install pygame -i https://pypi.tuna.tsinghua.edu.cn/simplepyaudio的安装（注意区分不同平台）windows pip install pyaudio -i https://pypi.tuna.tsinghua.edu.cn/simpleLinux   sudo apt install python3-pyaudiomac     brew install portaudiopip install pyaudio -i https://pypi.tuna.tsinghua.edu.cn/simple2.密钥说明：
每一个账号的用额只有500次数的请求，平时用足够使用了。
自行前往去注册：https://www.xfyun.cn/'''
import websocket
import datetime
import hashlib
import base64
import hmac
import json
from urllib.parse import urlencode
import time
import ssl
from wsgiref.handlers import format_date_time
from datetime import datetime
from time import mktime
import _thread as thread
import os
from pydub import AudioSegment
import time
import pygameSTATUS_FIRST_FRAME = 0  # 第一帧的标识
STATUS_CONTINUE_FRAME = 1  # 中间帧标识
STATUS_LAST_FRAME = 2  # 最后一帧的标识class Ws_Param(object):# 初始化def __init__(self, APPID, APIKey, APISecret, Text):self.APPID = APPIDself.APIKey = APIKeyself.APISecret = APISecretself.Text = Text# 公共参数(common)self.CommonArgs = {"app_id": self.APPID}# 业务参数(business)，更多个性化参数可在官网查看self.BusinessArgs = {"aue": "raw", "auf": "audio/L16;rate=16000", "vcn": "xiaofeng", "tte": "utf8"}self.Data = {"status": 2, "text": str(base64.b64encode(self.Text.encode('utf-8')), "UTF8")}# 生成urldef create_url(self):url = 'wss://tts-api.xfyun.cn/v2/tts'# 生成RFC1123格式的时间戳now = datetime.now()date = format_date_time(mktime(now.timetuple()))# 拼接字符串signature_origin = "host: " + "ws-api.xfyun.cn" + "\n"signature_origin += "date: " + date + "\n"signature_origin += "GET " + "/v2/tts " + "HTTP/1.1"# 进行hmac-sha256进行加密signature_sha = hmac.new(self.APISecret.encode('utf-8'), signature_origin.encode('utf-8'),digestmod=hashlib.sha256).digest()signature_sha = base64.b64encode(signature_sha).decode(encoding='utf-8')authorization_origin = "api_key=\"%s\", algorithm=\"%s\", headers=\"%s\", signature=\"%s\"" % (self.APIKey, "hmac-sha256", "host date request-line", signature_sha)authorization = base64.b64encode(authorization_origin.encode('utf-8')).decode(encoding='utf-8')# 将请求的鉴权参数组合为字典v = {"authorization": authorization,"date": date,"host": "ws-api.xfyun.cn"}# 拼接鉴权参数，生成urlurl = url + '?' + urlencode(v)# print("date: ",date)# print("v: ",v)# 此处打印出建立连接时候的url,参考本demo的时候可取消上方打印的注释，比对相同参数时生成的url与自己代码生成的url是否一致# print('websocket url :', url)return urldef on_message(ws, message):try:message =json.loads(message)code = message["code"]sid = message["sid"]audio = message["data"]["audio"]audio = base64.b64decode(audio)status = message["data"]["status"]# print(message)if status == 2:# print("ws is closed")ws.close()if code != 0:errMsg = message["message"]print("sid:%s call error:%s code is:%s" % (sid, errMsg, code))else:with open('./demo.pcm', 'ab') as f:f.write(audio)except Exception as e:print("receive msg,but parse exception:", e)# 收到websocket错误的处理
def on_error(ws, error):print("### error:", error)# 收到websocket关闭的处理
def on_close(ws,arg1,arg2):# print("### closed ###")passdef play_fun():# 加载PCM音频文件audio = AudioSegment.from_file("demo.pcm", format="raw", sample_width=2, frame_rate=16000, channels=1)# 将音频转换为MP3格式并播放audio.export("file.mp3", format="mp3")time.sleep(1)# # ==== windows 平台使用下面代码来播放音频，并将下面的代码注释# # 初始化pygame# pygame.mixer.init()# # 加载MP3文件# pygame.mixer.music.load("file.mp3")# # 播放MP3文件# pygame.mixer.music.play()# # 等待音频播放完毕# while pygame.mixer.music.get_busy():#     pygame.time.Clock().tick(10)# print("------ 播放完毕 ------")# ==== linux 平台使用下面代码来播放音频，并将上面的代码注释file = "file.mp3"os.system('mpg123 '+ file)def tts_fun(string_txr):# 收到websocket连接建立的处理def on_open(ws):def run(*args):d = {"common": wsParam.CommonArgs,"business": wsParam.BusinessArgs,"data": wsParam.Data,}d = json.dumps(d)print("------开始发送文本数据------")ws.send(d)if os.path.exists('./demo.pcm'):os.remove('./demo.pcm')thread.start_new_thread(run, ())# 测试时候在此处正确填写相关信息即可运行# 这里改成自己的key ,每一个人的用额都是有限的。https://console.xfyun.cn/services/iatwsParam = Ws_Param(APPID='d69356bc', APISecret='c3f938a4da84f7449bd2f958d461e7e1',APIKey='ZjE4ZGE4ZGU4YzViZmFhNTI0ZmYyNTE0',Text=string_txr)websocket.enableTrace(False)wsUrl = wsParam.create_url()ws = websocket.WebSocketApp(wsUrl, on_message=on_message, on_error=on_error, on_close=on_close)ws.on_open = on_openws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})def tts_main(input_txt):tts_fun(input_txt)play_fun()class tts_clss():def __init__(self, input_txt):tts_fun(input_txt)play_fun()if __name__ == "__main__":tts_main("你好，我是机器人！")

5.USB声卡可能报错

设置完默认声卡后，用Python录音和播放会出现一些错误提示，但发现录音和播放都正常，错误显示比如这样：

ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.center_lfe
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.side
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
ALSA lib confmisc.c:1281:(snd_func_refer) Unable to find definition ‘defaults.bluealsa.device’
ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
ALSA lib conf.c:4996:(snd_config_expand) Args evaluate error: No such file or directory
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM bluealsa
ALSA lib confmisc.c:1281:(snd_func_refer) Unable to find definition ‘defaults.bluealsa.device’
ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
ALSA lib conf.c:4996:(snd_config_expand) Args evaluate error: No such file or directory
ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM bluealsa
connect(2) call to /tmp/jack-1000/default/jack_0 failed (err=No such file or directory)
attempt to connect to server failed

为了不显示这些错误可以在Python代码里p = pyaudio.PyAudio() 之前加上：

os.close(sys.stderr.fileno())
http://www.lryc.cn/news/269500.html

相关文章：

  • 分布式系统架构设计之分布式系统实践案例和未来展望
  • 【办公软件】Excel双坐标轴图表
  • 彻底理解前端安全面试题（1）—— XSS 攻击，3种XSS攻击详解，建议收藏（含源码）
  • UE5.1_AI随机漫游
  • 智慧城市新型基础设施建设综合方案：文件全文52页，附下载
  • GitHub Copilot 终极详细介绍
  • LeetCode第63题 - 不同路径 II
  • python+django网上银行业务综合管理系统vue_bvj8b
  • 【软件工程】走进瀑布模型：传统软件开发的经典之路
  • 两个字符串间的最短路径问题 （100%用例）C卷 (JavaPythonNode.jsC语言C++)
  • 通过ADB来实现脚本来控制手机
  • 机器学习之K-means聚类
  • SSH 端口转发：如何将服务绑定到本地 IP 地址
  • 回归预测 | MATLAB实ZOA-LSTM基于斑马优化算法优化长短期记忆神经网络的多输入单输出数据回归预测模型 （多指标，多图）
  • python实现图像的二维傅里叶变换——冈萨雷斯数字图像处理
  • We are a team - 华为OD统一考试
  • NFC物联网智慧校园解决方案
  • 鸿蒙系列--组件介绍之容器组件
  • perl使用find函数踩坑
  • Java IDEA JUnit 单元测试
  • 深入理解 c++ 函数模板
  • 系列十二、Linux中安装Zookeeper
  • k8s之陈述式资源管理
  • 7天玩转 Golang 标准库之 http/net
  • 钡铼技术集IO数据采集可编程逻辑控制PLC无线4G环保物联网关
  • STM32CubeMX教程10 RTC 实时时钟 - 周期唤醒、闹钟A/B事件和备份寄存器
  • HarmonyOS4.0系统性深入开发08服务卡片架构
  • 002文章解读与程序——中国电机工程学报EI\CSCD\北大核心《计及源荷不确定性的综合能源生产单元运行调度与容量配置两阶段随机优化》已提供下载资源
  • Typora快捷键设置详细教程
  • 《异常检测——从经典算法到深度学习》25 基于深度隔离林的异常检测算法