Develop Reference

Exception: Failed to process waveform

Error:
Traceback (most recent call last):
File "c:\Programming\New_assistant\speech_to_text.py", line 18, in <module>
if rec.AcceptWaveform(data):
File "C:\Users\david\AppData\Local\Programs\Python\Python310\lib\site-packages\vosk\__init__.py", line 84, in AcceptWaveform
raise Exception("Failed to process waveform")
Exception: Failed to process waveform
PS C:\Programming\New_assistant>
I get this error when I try to use AcceptWaveform regardless of the file (wav) or the rest of the code, but the error is removed only when using vosk-model-small-ru-0.22, and does not give errors on vosk-model-ru-0.22, but the processing time is too long.
Code:
from vosk import Model, KaldiRecognizer
import json
import wave
model = Model(r"File\vosk-model-small-ru-0.22")
wf = wave.open(r"File\record1.wav", "rb")
rec = KaldiRecognizer(model, 8000)
result = ''
last_n = False
while True:
data = wf.readframes(8000)
if len(data) == 0:
break
if rec.AcceptWaveform(data):
res = json.loads(rec.Result())
if res['text'] != '':
result += f" {res['text']}"
last_n = False
elif not last_n:
result += '\n'
last_n = True
res = json.loads(rec.FinalResult())
result += f" {res['text']}"
print(result)

Using the poke method, I found a solution and got an assumption about the error occurring, so if I'm wrong or you have a more complete solution, add it and I'll mark it.
If you copied the sample code using vosk, then most likely this is the version with the module vosk-model-ru-0.22 which works with the sampling rate 8000,but vosk-model-small-ru-0.22 works with 44100, so just change 8000 to 44100 (depending on the entry)

Multiprocessing with text scraping

I want to scrape <p> from pages and since there will be a couple thousands of them I want to use multiprocessing. However, it doesn't work when I try to append the result to some variable
I want to append the result of scraping to the data = []
I made a url_common for a base website since some pages don't start with HTTP etc.
from tqdm import tqdm
import faster_than_requests as requests #20% faster on average in my case than urllib.request
import bs4 as bs
def scrape(link, data):
for i in tqdm(link):
if i[:3] !='htt':
url_common = 'https://www.common_url.com/'
else:
url_common = ''
try:
ht = requests.get2str(url_common + str(i))
except:
pass
parsed = bs.BeautifulSoup(ht,'lxml')
paragraphs = parsed.find_all('p')
for p in paragraphs:
data.append(p.text)
Above doesn't work, since map() doesn't accept function like above
I tried to use it another way:
def scrape(link):
for i in tqdm(link):
if i[:3] !='htt':
url_common = 'https://www.common_url.com/'
else:
url_common = ''
try:
ht = requests.get2str(url_common + str(i))
except:
pass
parsed = bs.BeautifulSoup(ht,'lxml')
paragraphs = parsed.find_all('p')
for p in paragraphs:
print(p.text)
from multiprocessing import Pool
p = Pool(10)
links = ['link', 'other_link', 'another_link']
data = p.map(scrape, links)
I get this error while using above function:
Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\lib\multiprocessing\process.py", line 297, in _bootstrap
self.run()
File "C:\ProgramData\Anaconda3\lib\multiprocessing\process.py", line 99, in run
self._target(*self._args, **self._kwargs)
File "C:\ProgramData\Anaconda3\lib\multiprocessing\pool.py", line 110, in worker
task = get()
File "C:\ProgramData\Anaconda3\lib\multiprocessing\queues.py", line 354, in get
return _ForkingPickler.loads(res)
AttributeError: Can't get attribute 'scrape' on <module '__main__' (built-in)>
I have not figured a way to do it so that it uses Pool and at the same time appending the result of scraping to the given variable
EDIT
I change a little bit to see where it stops:
def scrape(link):
for i in tqdm(link):
if i[:3] !='htt':
url_common = 'https://www.investing.com/'
else:
url_common = ''
try: #tries are always halpful with url as you never know
ht = requests.get2str(url_common + str(i))
except:
pass
print('works1')
parsed = bs.BeautifulSoup(ht,'lxml')
paragraphs = parsed.find_all('p')
print('works2')
for p in paragraphs:
print(p.text)
links = ['link', 'other_link', 'another_link']
scrape(links)
#WORKS PROPERLY AND PRINTS EVERYTHING
if __name__ == '__main__':
p = Pool(5)
print(p.map(scrape, links))
#DOESN'T WORK, NOTHING PRINTS. Error like above

You are using the map function incorrectly.
It iterates over each element of the iterable and calls the function on each element.
You can see the map function as doing something like the following:
to_be_mapped = [1, 2, 3]
mapped = []
def mapping(x): # <-- note that the mapping accepts a single value
return x**2
for item in to_be_mapped:
res = mapping(item)
mapped.append(res)
So to solve your problem remove the outermost for-loop as iterating is handled by the map function
def scrape(link):
if link[:3] !='htt':
url_common = 'https://www.common_url.com/'
else:
url_common = ''
try:
ht = requests.get2str(url_common + str(link))
except:
pass
parsed = bs.BeautifulSoup(ht,'lxml')
paragraphs = parsed.find_all('p')
for p in paragraphs:
print(p.text)

KeyError in Python Code even though Key is present

I am trying to create a Channel Separator code to separate the transcribe that is printed in a JSON file.
I have the following code:
import json
import boto3
def lambda_handler(event, context):
if event:
s3 = boto3.client("s3")
s3_object = event["Records"][0]["s3"]
bucket_name = s3_object["bucket"]["name"]
file_name = s3_object["object"]["key"]
file_obj = s3.get_object(Bucket=bucket_name, Key=file_name)
transcript_result = json.loads(file_obj["Body"].read())
segmented_transcript = transcript_result["results"]["channel_labels"]
items = transcript_result["results"]["items"]
channel_text = []
flag = False
channel_json = {}
for no_of_channel in range (segmented_transcript["number_of_channels"]):
for word in items:
for cha in segmented_transcript["channels"]:
if cha["channel_label"] == "ch_"+str(no_of_channel):
end_time = cha["end_time"]
if "start_time" in word:
if cha["items"]:
for cha_item in cha["items"]:
if word["end_time"] == cha_item["end_time"] and word["start_time"] == cha_item["start_time"]:
channel_text.append(word["alternatives"][0]["content"])
flag = True
elif word["type"] == "punctuation":
if flag and channel_text:
temp = channel_text[-1]
temp += word["alternatives"][0]["content"]
channel_text[-1] = temp
flag = False
break
channel_json["ch_"+str(no_of_channel)] = ' '.join(channel_text)
channel_text = []
print(channel_json)
s3.put_object(Bucket="aws-speaker-separation", Key=file_name, Body=json.dumps(channel_json))
return{
'statusCode': 200,
'body': json.dumps('Channel transcript separated successfully!')
}
However, when I run it, I get an error on line 23 saying:
[ERROR] KeyError: 'end_time'
Traceback (most recent call last):
File "/var/task/lambda_function.py", line 23, in lambda_handler
end_time = cha["end_time"]
I am confused as to why this error is happening as in my JSON code, the things to read are as follows:
JSON Code Parameters
Any ideas why this error is appearing?

cha is a channel, the end_time is a layer deeper in the items of your channel. To access the items of your channel do:
for item in cha["items"]:
print(item["end_time"])

Python zlib error while bruteforcing protected zip file

Basically, i'm trying to write a script to bruteforce a protected zip file in python that tries every character combination (i.e. aa,ba,ca,da etc). But after a few tries it retrieves a strange error, and i'm not being able to find nowhere a solution for it.
Program:
import zipfile as z
class zipVictim:
def __init__(self,file):
self.found = False
self.password = ''
self.file = file
self.extracted_file_list = []
def bruteforceAttack(self,start_char: int,end_char: int,length: int,deep_loop=False,print_mode=False):
"""
Doc
"""
def _loop_chain(self,file,start_char,end_char,length):
lList = []
sPass = ''
iAttempt = 1
for iInc in range(length):
lList.append(start_char)
while lList[len(lList)-1] < end_char:
for iInc2 in range(start_char,end_char):
for iInc3 in range(len(lList)):
sPass = sPass + chr(lList[iInc3])
if iInc3 == 0:
lList[iInc3] = lList[iInc3] + 1
elif lList[iInc3 -1] > end_char:
lList[iInc3] = lList[iInc3] + 1
lList[iInc3 -1] = start_char
try:
if print_mode:
print("Attempt %s, password: %s" % (iAttempt,sPass),end='\r')
iAttempt = iAttempt + 1
oFile.extractall(pwd=sPass.encode())
self.extracted_file_list = oFile.namelist()
self.password = sPass
self.found = True
return self.found
except RuntimeError:
pass
sPass = ''
return self.found
oFile = self.file
if not deep_loop:
_loop_chain(self,oFile,start_char,end_char,length)
else:
for iInc in range(length):
_loop_chain(self,oFile,start_char,end_char,iInc+1)
if __name__ == '__main__':
file = z.ZipFile('data.zip')
s = zipVictim(file)
s.bruteforceAttack(64,125,2,print_mode=True)
Error Retrieved:
Traceback (most recent call last):
File "C:\Program Files (x86)\Microsoft Visual Studio\Shared\Python36_64\lib\zipfile.py", line 925, in _read1
data = self._decompressor.decompress(data, n)
zlib.error: Error -3 while decompressing data: invalid block type
Does anybody know what trigger this error and how to solve it?

Permissions, Python Script

I am learning to write Python Scripts for work and I have run into some problems. The script is supposed to read a file, and print the permissions to an email. My problem is I am getting an error when it tries to call the permission() method, and I don't know how to fix it.
Python Code
import smtplib
import os
import stat
result = ""
def permission(file):
s = os.stat(file)
mode = s.st_mode
if(stat.S_IRUSR & mode):
ownerRead = 1
result += ownerRead
else:
ownerRead = 0
result += ownerRead
if(stat.S_IWUSR & mode):
ownerWrite = 1
result += ownerWrite
else:
ownerWrite = 0
result += ownerWrite
if(stat.S_IXUSR & mode):
ownerExecute = 1
result += ownerExecute
else:
ownerExecute = 0
result += ownerExecute
if(stat.S_IRGRP & mode):
groupRead = 1
result += groupRead
else:
groupRead = 0
result += groupRead
if(stat.S_IWGRP & mode):
groupWrite = 1
result += groupWrite
else:
groupWrite = 0
result += groupWrite
if(stat.S_IXGRP & mode):
groupExecute = 1
result += groupExecute
else:
groupExecute = 0
result += groupExecute
if(stat.S_IROTH & mode):
otherRead = 1
result += otherRead
else:
otherRead = 0
result += otherRead
if(stat.S_IWOTH & mode):
otherWrite = 1
result += otherWrite
else:
otherWrite = 0
result += otherWrite
if(stat.S_IXOTH & mode):
otherExecute = 1
result += otherExecute
else:
otherExecute = 0
result += otherExecute
return result
to = 'email#yahoo.com'
gmail_user = 'email#gmail.com'
gmail_pwd = 'pwd'
smtpserver = smtplib.SMTP("smtp.gmail.com",587)
smtpserver.ehlo()
smtpserver.starttls()
smtpserver.ehlo
smtpserver.login(gmail_user, gmail_pwd)
header = 'To:' + to + '\n' + 'From: ' + gmail_user + '\n' + 'Subject:permissions \n'
print header
values = permission(file)
print values
msg = header + values
smtpserver.sendmail(gmail_user, to, msg)
print 'done!'
smtpserver.close()
Error Output
Traceback (most recent call last):
File "lastpart.py", line 83, in <module>
values = permission(file)
File "lastpart.py", line 15, in permission
s = os.stat(file)
TypeError: coercing to Unicode: need string or buffer, type found

You fix it by passing the actual filename to the function, not the file built-in type.

>>> file
<type 'file'>
Name your variable something other than file, and actually pass a filename to it. You never actually define the thing you're passing to your call of the function, and thus the only reason it's not crashing with an undefined variable error is because Python happens to already define something with that name, built-in.