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/
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/simple
pyaudio的安装（注意区分不同平台）
windows pip install pyaudio -i https://pypi.tuna.tsinghua.edu.cn/simple
Linux sudo apt install python3-pyaudio
mac brew install portaudio
pip install pyaudio -i https://pypi.tuna.tsinghua.edu.cn/simple
2.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 thread
STATUS_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 = APPID
self.APIKey = APIKey
self.APISecret = APISecret
self.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url
def 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url
url = 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):
pass
def 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 = 1024
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
RECORD_SECONDS =time
WAVE_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_open
ws.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/simple
pyaudio的安装（注意区分不同平台）
windows pip install pyaudio -i https://pypi.tuna.tsinghua.edu.cn/simple
Linux sudo apt install python3-pyaudio
mac brew install portaudio
pip install pyaudio -i https://pypi.tuna.tsinghua.edu.cn/simple
2.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 pygame
STATUS_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 = APPID
self.APIKey = APIKey
self.APISecret = APISecret
self.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url
def 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url
url = 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
def 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 ###")
pass
def 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/iat
wsParam = 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_open
ws.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())
