Skip to content

T
TV_OCR
Commit 7b6f8043 by mucece
Options

Merge remote-tracking branch 'TV_OCR/master' into muce

parents b0417193 2c4e0dd0
Showing with 36 additions and 490 deletions
TV_OCR/build/initial/Analysis-00.toc
This source diff could not be displayed because it is too large. You can view the blob instead.
TV_OCR/build/initial/COLLECT-00.toc
This source diff could not be displayed because it is too large. You can view the blob instead.
TV_OCR/build/initial/EXE-00.toc
......@@ -51,7 +51,7 @@
[],
False,
False,
1638438345,
1645430499,
[('runw.exe',
'D:\\python3.8\\lib\\site-packages\\PyInstaller\\bootloader\\Windows-64bit\\runw.exe',
'EXECUTABLE')])
TV_OCR/build/initial/warn-initial.txt
......@@ -15,6 +15,7 @@ IMPORTANT: Do NOT post this list to the issue-tracker. Use it as a basis for
yourself tracking down the missing module. Thanks!
missing module named pyimod03_importers - imported by D:\python3.8\Lib\site-packages\PyInstaller\hooks\rthooks\pyi_rth_pkgutil.py (top-level), D:\python3.8\Lib\site-packages\PyInstaller\hooks\rthooks\pyi_rth_pkgres.py (top-level)
missing module named _manylinux - imported by pkg_resources._vendor.packaging.tags (delayed, optional), packaging._manylinux (delayed, optional), setuptools._vendor.packaging.tags (delayed, optional)
missing module named _posixshmem - imported by multiprocessing.resource_tracker (conditional), multiprocessing.shared_memory (conditional)
missing module named multiprocessing.set_start_method - imported by multiprocessing (top-level), multiprocessing.spawn (top-level)
missing module named multiprocessing.get_start_method - imported by multiprocessing (top-level), multiprocessing.spawn (top-level)
......@@ -29,27 +30,26 @@ missing module named multiprocessing.TimeoutError - imported by multiprocessing
missing module named _scproxy - imported by urllib.request (conditional)
missing module named termios - imported by tty (top-level), getpass (optional)
missing module named pwd - imported by posixpath (delayed, conditional), shutil (optional), tarfile (optional), pathlib (delayed, conditional, optional), http.server (delayed, optional), webbrowser (delayed), netrc (delayed, conditional), getpass (delayed), distutils.util (delayed, conditional, optional), distutils.archive_util (optional)
missing module named 'org.python' - imported by copy (optional), setuptools.sandbox (conditional), xml.sax (delayed, conditional)
missing module named 'java.lang' - imported by platform (delayed, optional), xml.sax._exceptions (conditional)
missing module named multiprocessing.BufferTooShort - imported by multiprocessing (top-level), multiprocessing.connection (top-level)
missing module named multiprocessing.AuthenticationError - imported by multiprocessing (top-level), multiprocessing.connection (top-level)
missing module named asyncio.DefaultEventLoopPolicy - imported by asyncio (delayed, conditional), asyncio.events (delayed, conditional)
missing module named 'org.python' - imported by pickle (optional), setuptools.sandbox (conditional), xml.sax (delayed, conditional)
missing module named org - imported by pickle (optional)
missing module named _uuid - imported by uuid (optional)
missing module named netbios - imported by uuid (delayed)
missing module named win32wnet - imported by uuid (delayed)
missing module named readline - imported by cmd (delayed, conditional, optional), code (delayed, conditional, optional), pdb (delayed, optional)
missing module named __builtin__ - imported by torch._six (conditional), pkg_resources._vendor.pyparsing (conditional), pyparsing (conditional), setuptools._vendor.pyparsing (conditional)
missing module named ordereddict - imported by pkg_resources._vendor.pyparsing (optional), pyparsing (optional), setuptools._vendor.pyparsing (optional)
missing module named org - imported by copy (optional)
missing module named _manylinux - imported by pkg_resources._vendor.packaging.tags (delayed, optional), packaging._manylinux (delayed, optional), setuptools._vendor.packaging.tags (delayed, optional)
missing module named grp - imported by shutil (optional), tarfile (optional), pathlib (delayed), distutils.archive_util (optional)
missing module named 'pkg_resources.extern.pyparsing' - imported by pkg_resources._vendor.packaging.markers (top-level), pkg_resources._vendor.packaging.requirements (top-level)
missing module named 'win32com.shell' - imported by pkg_resources._vendor.appdirs (conditional, optional)
missing module named 'com.sun' - imported by pkg_resources._vendor.appdirs (delayed, conditional, optional)
missing module named com - imported by pkg_resources._vendor.appdirs (delayed)
missing module named win32api - imported by distutils.msvccompiler (optional), pkg_resources._vendor.appdirs (delayed, conditional, optional)
missing module named win32com - imported by pkg_resources._vendor.appdirs (delayed)
missing module named _winreg - imported by platform (delayed, optional), pkg_resources._vendor.appdirs (delayed, conditional)
missing module named 'pkg_resources.extern.pyparsing' - imported by pkg_resources._vendor.packaging.markers (top-level), pkg_resources._vendor.packaging.requirements (top-level)
missing module named pkg_resources.extern.packaging - imported by pkg_resources.extern (top-level), pkg_resources (top-level)
missing module named pkg_resources.extern.appdirs - imported by pkg_resources.extern (top-level), pkg_resources (top-level)
missing module named vms_lib - imported by platform (delayed, conditional, optional)
......@@ -98,7 +98,7 @@ missing module named 'PySide6.QtGui' - imported by PIL.ImageQt (conditional, opt
missing module named 'PyQt6.QtGui' - imported by PIL.ImageQt (conditional, optional)
missing module named dummy_thread - imported by cffi.lock (conditional, optional)
missing module named thread - imported by cffi.lock (conditional, optional), cffi.cparser (conditional, optional)
missing module named 'setuptools.extern.pyparsing' - imported by setuptools._vendor.packaging.markers (top-level), setuptools._vendor.packaging.requirements (top-level)
missing module named 'setuptools.extern.pyparsing' - imported by setuptools._vendor.packaging.requirements (top-level), setuptools._vendor.packaging.markers (top-level)
missing module named 'setuptools.extern.more_itertools' - imported by setuptools.dist (top-level), setuptools.package_index (top-level), setuptools.msvc (top-level)
missing module named 'setuptools.extern.packaging.version' - imported by setuptools.config (top-level), setuptools.msvc (top-level)
missing module named wincertstore - imported by setuptools.ssl_support (delayed, optional)
......
TV_OCR/build/initial/xref-initial.html
......@@ -41,6 +41,7 @@ imports:
&#8226; <a href="#collections">collections</a>
&#8226; <a href="#collections.abc">collections.abc</a>
&#8226; <a href="#copyreg">copyreg</a>
&#8226; <a href="#difflib">difflib</a>
&#8226; <a href="#encodings">encodings</a>
&#8226; <a href="#encodings.aliases">encodings.aliases</a>
&#8226; <a href="#encodings.ascii">encodings.ascii</a>
......@@ -444,7 +445,7 @@ imported by:
<a target="code" href="" type="text/plain"><tt>'org.python'</tt></a>
<span class="moduletype">MissingModule</span> <div class="import">
imported by:
<a href="#pickle">pickle</a>
<a href="#copy">copy</a>
&#8226; <a href="#setuptools.sandbox">setuptools.sandbox</a>
&#8226; <a href="#xml.sax">xml.sax</a>
......@@ -661,7 +662,6 @@ imports:
&#8226; <a href="#PIL.ImageShow">PIL.ImageShow</a>
&#8226; <a href="#PIL.ImageStat">PIL.ImageStat</a>
&#8226; <a href="#PIL.ImageTk">PIL.ImageTk</a>
&#8226; <a href="#PIL.Jpeg2KImagePlugin">PIL.Jpeg2KImagePlugin</a>
&#8226; <a href="#PIL.JpegImagePlugin">PIL.JpegImagePlugin</a>
&#8226; <a href="#PIL.PaletteFile">PIL.PaletteFile</a>
&#8226; <a href="#PIL.PdfParser">PIL.PdfParser</a>
......@@ -1824,8 +1824,7 @@ imports:
</div>
<div class="import">
imported by:
<a href="#PIL">PIL</a>
&#8226; <a href="#PIL.IcnsImagePlugin">PIL.IcnsImagePlugin</a>
<a href="#PIL.IcnsImagePlugin">PIL.IcnsImagePlugin</a>
&#8226; <a href="#PIL.Image">PIL.Image</a>
</div>
......@@ -6828,8 +6827,8 @@ imported by:
<a target="code" href="///D:/python3.8/lib/copy.py" type="text/plain"><tt>copy</tt></a>
<span class="moduletype">SourceModule</span> <div class="import">
imports:
<a href="#copyreg">copyreg</a>
&#8226; <a href="#org">org</a>
<a href="#'org.python'">'org.python'</a>
&#8226; <a href="#copyreg">copyreg</a>
&#8226; <a href="#types">types</a>
&#8226; <a href="#weakref">weakref</a>
......@@ -7400,6 +7399,7 @@ imports:
imported by:
<a href="#difflib">difflib</a>
&#8226; <a href="#doctest">doctest</a>
&#8226; <a href="#initial.py">initial.py</a>
&#8226; <a href="#numpy.testing._private.utils">numpy.testing._private.utils</a>
&#8226; <a href="#test_rec_infer_live">test_rec_infer_live</a>
&#8226; <a href="#torch.jit">torch.jit</a>
......@@ -23540,7 +23540,7 @@ imported by:
<a target="code" href="" type="text/plain"><tt>org</tt></a>
<span class="moduletype">MissingModule</span> <div class="import">
imported by:
<a href="#copy">copy</a>
<a href="#pickle">pickle</a>
</div>
......@@ -23855,7 +23855,6 @@ imports:
<a href="#packaging">packaging</a>
&#8226; <a href="#packaging.__about__">packaging.__about__</a>
&#8226; <a href="#packaging._manylinux">packaging._manylinux</a>
&#8226; <a href="#packaging._musllinux">packaging._musllinux</a>
&#8226; <a href="#packaging.version">packaging.version</a>
&#8226; <a href="#pkg_resources">pkg_resources</a>
......@@ -23945,8 +23944,7 @@ imports:
</div>
<div class="import">
imported by:
<a href="#packaging">packaging</a>
&#8226; <a href="#packaging.tags">packaging.tags</a>
<a href="#packaging.tags">packaging.tags</a>
&#8226; <a href="#pkg_resources">pkg_resources</a>
</div>
......@@ -24205,8 +24203,7 @@ imported by:
<a target="code" href="///D:/python3.8/lib/pickle.py" type="text/plain"><tt>pickle</tt></a>
<span class="moduletype">SourceModule</span> <div class="import">
imports:
<a href="#'org.python'">'org.python'</a>
&#8226; <a href="#_compat_pickle">_compat_pickle</a>
<a href="#_compat_pickle">_compat_pickle</a>
&#8226; <a href="#_pickle">_pickle</a>
&#8226; <a href="#codecs">codecs</a>
&#8226; <a href="#copyreg">copyreg</a>
......@@ -24214,6 +24211,7 @@ imports:
&#8226; <a href="#functools">functools</a>
&#8226; <a href="#io">io</a>
&#8226; <a href="#itertools">itertools</a>
&#8226; <a href="#org">org</a>
&#8226; <a href="#pprint">pprint</a>
&#8226; <a href="#re">re</a>
&#8226; <a href="#struct">struct</a>
TV_OCR/dist/initial/xunfei/iat_ws_python3.py deleted 100644 → 0
# -*- coding:utf-8 -*-
#
# author: iflytek
#
# 本demo测试时运行的环境为：Windows + Python3.7
# 本demo测试成功运行时所安装的第三方库及其版本如下，您可自行逐一或者复制到一个新的txt文件利用pip一次性安装：
# cffi==1.12.3
# gevent==1.4.0
# greenlet==0.4.15
# pycparser==2.19
# six==1.12.0
# websocket==0.2.1
# websocket-client==0.56.0
#
# 语音听写流式 WebAPI 接口调用示例 接口文档（必看）：https://doc.xfyun.cn/rest_api/语音听写（流式版）.html
# webapi 听写服务参考帖子（必看）：http://bbs.xfyun.cn/forum.php?mod=viewthread&tid=38947&extra=
# 语音听写流式WebAPI 服务，热词使用方式：登陆开放平台https://www.xfyun.cn/后，找到控制台--我的应用---语音听写（流式）---服务管理--个性化热词，
# 设置热词
# 注意：热词只能在识别的时候会增加热词的识别权重，需要注意的是增加相应词条的识别率，但并不是绝对的，具体效果以您测试为准。
# 语音听写流式WebAPI 服务，方言试用方法：登陆开放平台https://www.xfyun.cn/后，找到控制台--我的应用---语音听写（流式）---服务管理--识别语种列表
# 可添加语种或方言，添加后会显示该方言的参数值
# 错误码链接：https://www.xfyun.cn/document/error-code （code返回错误码时必看）
# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
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_Param1(object):
# 初始化
def __init__(self):
self.APPID = '5d1ad3d5'
self.APIKey ='b7c216ce0834468cc372f3f00d2d7b36'
self.APISecret = '28c7560f3d6ec49f8c8750b76002ab34'
self.AudioFile='luyin.wav'
self.result=""
# 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,"ptt":0}
# 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)["data"]["result"])
global result
# result=[]
for i in data:
for w in i["cw"]:
wsParam1.result += w["w"]
# print(result)
# print("sid:%s call success!,data is:%s" % (sid, json.dumps(data, ensure_ascii=False)))
# for i in len(data):
# print(data[int(i)]["cw"][0]["w"])
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):
print("### closed ###")
# 收到websocket连接建立的处理
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 # 音频的状态信息，标识音频是第一帧，还是中间帧、最后一帧
with open(wsParam1.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": wsParam1.CommonArgs,
"business": wsParam1.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 translation():
# print(wsParam)
# wsParam1=ws
time1 = datetime.now()
global wsParam1
wsParam1 = Ws_Param1()
websocket.enableTrace(False)
wsUrl = wsParam1.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()
print(time2 - time1)
return wsParam1.result
if __name__ == "__main__":
# 测试时候在此处正确填写相关信息即可运行
result=translation()
time.sleep(3)
print(result)
TV_OCR/dist/initial/xunfei/record.py deleted 100644 → 0
import os
import sys
import time
import wave
import numpy as np
import pyaudio
from scipy import fftpack
"""
监控麦克风，以及进行录音
"""
class record():
#判断声音是否超过一定数值
def recording_time(self):
CHUNK = 1024 # 块大小
FORMAT = pyaudio.paInt16 # 每次采集的位数
CHANNELS = 1
RATE = 16000 # 采样率：每秒采集数据的次数
self.end_time = None
p = pyaudio.PyAudio()
stream = p.open(format=FORMAT, channels=CHANNELS, rate=RATE, input=True, frames_per_buffer=CHUNK)
print("录音中")
frames = []
time1 = time.time()
while True:
data = stream.read(CHUNK)
rt_data = np.frombuffer(data, np.dtype('<i2'))
# print(rt_data*10)
# 傅里叶变换
fft_temp_data = fftpack.fft(rt_data, rt_data.size, overwrite_x=True)
fft_data = np.abs(fft_temp_data)[0:fft_temp_data.size // 2 + 1]
fa_data = sum(fft_data) // len(fft_data)
print(fa_data)
time2 = time.time()
if fa_data > 2000:
self.end_time = time.time()
print("有反馈")
return self.end_time
elif time2 - time1 > 3:
return self.end_time
def recording(self):
CHUNK = 1024 # 块大小
FORMAT = pyaudio.paInt16 # 每次采集的位数
CHANNELS = 1
RATE = 16000 # 采样率：每秒采集数据的次数
self.end_time=None
WAVE_OUTPUT_FILENAME = "luyin.wav" # 文件存放位置
self.break_luyin = False
self.start_luyin = False
p = pyaudio.PyAudio()
stream = p.open(format=FORMAT, channels=CHANNELS, rate=RATE, input=True, frames_per_buffer=CHUNK)
print("录音中")
frames = []
data_list = [0] * 60
# while not self.break_luyin:
time_start=time.time()
while True:
if self.break_luyin or (time.time()-time_start)>10:
break
data = stream.read(CHUNK)
rt_data = np.frombuffer(data, np.dtype('<i2'))
# print(rt_data*10)
# 傅里叶变换
fft_temp_data = fftpack.fft(rt_data, rt_data.size, overwrite_x=True)
fft_data = np.abs(fft_temp_data)[0:fft_temp_data.size // 2 + 1]
fa_data = sum(fft_data) // len(fft_data)
print(fa_data)
data_list.pop(0)
data_list.append(fa_data)
if fa_data > 1000:
self.start_luyin = True
if self.start_luyin:
kkk = lambda x: float(x) < 900
if all([kkk(i) for i in data_list]):
self.break_luyin = True
frames = frames[:-55]
if self.start_luyin:
frames.append(data)
print("* 录音结束")
stream.stop_stream()
stream.close()
p.terminate()
if os.path.exists(WAVE_OUTPUT_FILENAME):
os.remove(WAVE_OUTPUT_FILENAME)
with wave.open(WAVE_OUTPUT_FILENAME, 'wb') as wf:
wf.setnchannels(CHANNELS)
wf.setsampwidth(p.get_sample_size(FORMAT))
wf.setframerate(RATE)
wf.writeframes(b''.join(frames))
if __name__ == '__main__':
c=record()
c.recording()
\ No newline at end of file
TV_OCR/dist/initial/xunfei/tts_ws_python3_demo.py deleted 100644 → 0
import wave
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 xpinyin import Pinyin
from playsound import playsound
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": "lame","sfl":1, "auf": "audio/L16;rate=16000", "vcn": "xiaoyan", "tte": "utf8", "speed": 20,"volume":100}
self.Data = {"status": 2, "text": str(base64.b64encode(self.Text.encode('utf-8')), "UTF8")}
#使用小语种须使用以下方式，此处的unicode指的是 utf16小端的编码方式，即"UTF-16LE"”
#self.Data = {"status": 2, "text": str(base64.b64encode(self.Text.encode('utf-16')), "UTF8")}
def set_BusinessArgs(self,vcn,volume):
self.BusinessArgs={"aue": "lame","sfl":1, "auf": "audio/L16;rate=16000", "vcn": vcn, "tte": "utf8", "speed": 50,"volume":volume}
# 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('./text.mp3', '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):
print("### closed ###")
# 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('./text.mp3'):
os.remove('./text.mp3')
thread.start_new_thread(run, ())
def skip_video(self,text,vcn,volume):
# 测试时候在此处正确填写相关信息即可运行
global wsParam
self.set_BusinessArgs(self,vcn,volume)
wsParam = Ws_Param(APPID='5d1ad3d5', APISecret='28c7560f3d6ec49f8c8750b76002ab34',
APIKey='b7c216ce0834468cc372f3f00d2d7b36',
Text=text)
websocket.enableTrace(False)
wsUrl = wsParam.create_url()
ws = websocket.WebSocketApp(wsUrl, on_message=Ws_Param.on_message, on_error=Ws_Param.on_error, on_close=Ws_Param.on_close)
ws.on_open =Ws_Param.on_open
ws.run_forever(sslopt={"cert_reqs": ssl.CERT_NONE})
print("转换完成")
def pcm2wav(self,pcm_file, wav_file, channels=1, bits=16, sample_rate=16000):
pcmf = open(pcm_file, 'rb')
pcmdata = pcmf.read()
pcmf.close()
if bits % 8 != 0:
raise ValueError("bits % 8 must == 0. now bits:" + str(bits))
wavfile = wave.open(wav_file, 'wb')
wavfile.setnchannels(channels)
wavfile.setsampwidth(bits // 8)
wavfile.setframerate(sample_rate)
wavfile.writeframes(pcmdata)
wavfile.close()
if __name__ == '__main__':
# A=Ws_Param(APPID='5d1ad3d5', APISecret='28c7560f3d6ec49f8c8750b76002ab34',
# APIKey='b7c216ce0834468cc372f3f00d2d7b36',Text="")
Ws_Param.skip_video(self= Ws_Param,text='小艺小艺',vcn="kaiselin",volume=100)
p=Pinyin()
print(p.get_pinyin("小菊",""))
# A.pcm2wav('nnn.pcm',"nnn.wav")
playsound("text.mp3")
# play_mp3('nn.wav')
\ No newline at end of file
TV_OCR/rec_infer_live.py
......@@ -2,6 +2,8 @@
import os
import sys
import pathlib
import re
import cv2
import numpy as np
import difflib
......@@ -159,6 +161,7 @@ class run():
#根据概率值执行过滤
self.words= run.text_filter(out)
#不过滤
# self.words = out[0][0]
#如果有识别结果且未被过滤
......@@ -179,8 +182,14 @@ class run():
def get_equal_rate_1(str1, str2):
return difflib.SequenceMatcher(None, str1, str2).quick_ratio()
#更正识别出错的文字
def correct(string,errorWord,rightWord):
if re.search(errorWord,string):
string=string.replace(errorWord,rightWord)
return string
if __name__ == '__main__':
ru=run()
ru.ocr_video(1)
print(ru.words)
# ru=run()
# ru.ocr_video(1)
# print(ru.words)
# name=ru.ocr_video(0)
print(correct("我想看甄传",'甄媛传','甄嬛传'))
\ No newline at end of file
TV_OCR/test_rec_infer_live.py
......@@ -189,6 +189,8 @@ class run():
# self.words= run.text_filter(out)
# 不过滤
self.words = out[0][0]
# 替换识别出错的甄嬛传
self.words=correct(self.words,"甄媛传",'甄嬛传')
#根据相似度取相似度结果最高的
similarity =get_equal_rate_1(self.words,text)
similarity1 = get_equal_rate_1(self.final_text,text)
......@@ -258,7 +260,11 @@ def delet_fuhao(words):
tuple1.append(n)
new_text = "".join(tuple1)
return new_text
#更正识别出错的文字
def correct(string,errorWord,rightWord):
if re.search(errorWord,string):
string=string.replace(errorWord,rightWord)
return string
# if __name__ == '__main__':
......
TV_OCR/text.mp3
No preview for this file type
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment