I'm newbie and trying to use the google-cloud speech-to-text with python and multiprocessing. Here is a simple example to reproduce my issue. I'm running the code on Windows.
When I run the code without multiprocessing, it works fine.
import io
from tqdm import tqdm
from multiprocessing import Pool, freeze_support, cpu_count
from google.cloud import speech
from google.cloud.speech import enums
from google.cloud.speech import types
# Instantiates a client
CLIENT = speech.SpeechClient()
def speech_to_text(file_name, language= "en-US"):
with io.open(file_name, 'rb') as audio_file:
content = audio_file.read()
audio = types.RecognitionAudio(content=content)
config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.ENCODING_UNSPECIFIED,
sample_rate_hertz=16000,
language_code= language)
# Detects speech in the audio file
response = CLIENT.recognize(config, audio)
transcript = ""
if len(response.results):
transcript = response.results[0].alternatives[0].transcript
return transcript
def worker(ix):
audio_file_name = "audio.mp3"
transcript = speech_to_text(audio_file_name)
if __name__ == "__main__":
n_cores = cpu_count() - 1
freeze_support() # for Windows support
with Pool(n_cores) as p:
max_ = len(range(2))
with tqdm(total=max_) as pbar:
for i, result in enumerate(tqdm(p.imap_unordered(worker, range(2)))):
pbar.update()
Here is the Error message that I get:
Traceback (most recent call last):
File "C:\Users\me\Anaconda3\lib\multiprocessing\spawn.py", line 114, in _main
prepare(preparation_data)
File "C:\Users\me\Anaconda3\lib\multiprocessing\spawn.py", line 225, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "C:\Users\me\Anaconda3\lib\multiprocessing\spawn.py", line 277, in _fixup_main_from_path
run_name="__mp_main__")
File "C:\Users\me\Anaconda3\lib\runpy.py", line 263, in run_path
pkg_name=pkg_name, script_name=fname)
File "C:\Users\me\Anaconda3\lib\runpy.py", line 96, in _run_module_code
mod_name, mod_spec, pkg_name, script_name)
File "C:\Users\me\Anaconda3\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "C:\Users\me\Desktop\outCaptcha\multiproc.py", line 10, in <module>
from google.cloud import speech
File "C:\Users\me\.virtualenvs\outCaptcha\lib\site-packages\google\cloud\speech.py", line 20, in <module>
from google.cloud.speech_v1 import SpeechClient
File "C:\Users\me\.virtualenvs\outCaptcha\lib\site-packages\google\cloud\speech_v1\__init__.py", line 17, in <module>
from google.cloud.speech_v1.gapic import speech_client
File "C:\Users\me\.virtualenvs\outCaptcha\lib\site-packages\google\cloud\speech_v1\gapic\speech_client.py", line 23, in <module>
import google.api_core.client_options
File "C:\Users\me\.virtualenvs\outCaptcha\lib\site-packages\google\api_core\__init__.py", line 23, in <module>
__version__ = get_distribution("google-api-core").version
File "C:\Users\me\AppData\Roaming\Python\Python37\site-packages\pkg_resources\__init__.py", line 481, in get_distribution
dist = get_provider(dist)
File "C:\Users\me\AppData\Roaming\Python\Python37\site-packages\pkg_resources\__init__.py", line 357, in get_provider
return working_set.find(moduleOrReq) or require(str(moduleOrReq))[0]
File "C:\Users\me\AppData\Roaming\Python\Python37\site-packages\pkg_resources\__init__.py", line 900, in require
needed = self.resolve(parse_requirements(requirements))
File "C:\Users\me\AppData\Roaming\Python\Python37\site-packages\pkg_resources\__init__.py", line 786, in resolve
raise DistributionNotFound(req, requirers)
pkg_resources.DistributionNotFound: The 'google-api-core' distribution was not found and is required by the application
Thanks a lot for your help. Please let me know if you need any details about the issue
In my case this solved the problem.
I hope this helps.