Skip to content

tools.py crashes after splitting the audio data when i click "Run Dataset Builder", or trying to upload a wav file using the Diarization option #4

@WiccyShackleton

Description

@WiccyShackleton

tools.py crashes after clicking "Run dataset builder", it splits the audio up but crashes at the first transcription attempt, no error, just closes the window. any attempt to import the csv afterwards causes the app to crash and quit again. Also when trying the Diarization option the upload times-out.

I get this from the console in anaconda

Transcribing entry 1

(myenv) C:\Users\ukbig\Documents\GitHub\TTS-dataset-tools>python tools.py

(myenv) C:\Users\ukbig\Documents\GitHub\TTS-dataset-tools>python tools.py
Uploading C:\Users\ukbig\Music\JOB/6127495.wav to google cloud storage bucket
Traceback (most recent call last):
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\connectionpool.py", line 703, in urlopen
httplib_response = self._make_request(
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\connectionpool.py", line 398, in _make_request
conn.request(method, url, **httplib_request_kw)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\connection.py", line 239, in request
super(HTTPConnection, self).request(method, url, body=body, headers=headers)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1256, in request
self._send_request(method, url, body, headers, encode_chunked)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1302, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1251, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1050, in _send_output
self.send(chunk)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 972, in send
self.sock.sendall(data)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\ssl.py", line 1204, in sendall
v = self.send(byte_view[count:])
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\ssl.py", line 1173, in send
return self._sslobj.write(data)
socket.timeout: The write operation timed out

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\requests\adapters.py", line 489, in send
resp = conn.urlopen(
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\connectionpool.py", line 787, in urlopen
retries = retries.increment(
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\util\retry.py", line 550, in increment
raise six.reraise(type(error), error, _stacktrace)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\packages\six.py", line 769, in reraise
raise value.with_traceback(tb)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\connectionpool.py", line 703, in urlopen
httplib_response = self._make_request(
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\connectionpool.py", line 398, in _make_request
conn.request(method, url, **httplib_request_kw)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\connection.py", line 239, in request
super(HTTPConnection, self).request(method, url, body=body, headers=headers)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1256, in request
self._send_request(method, url, body, headers, encode_chunked)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1302, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1251, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1050, in _send_output
self.send(chunk)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 972, in send
self.sock.sendall(data)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\ssl.py", line 1204, in sendall
v = self.send(byte_view[count:])
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\ssl.py", line 1173, in send
return self._sslobj.write(data)
urllib3.exceptions.ProtocolError: ('Connection aborted.', timeout('The write operation timed out'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "tools.py", line 70, in run_google_speech_call
builder.diarization(get_value("label_wav_file_transcribe"), get_value("input_storage_bucket"), get_value("input_project_name"))
File "C:\Users\ukbig\Documents\GitHub\TTS-dataset-tools\dataset_builder.py", line 395, in diarization
self.upload_blob(bucket_name, wavfile, "temp_audio.wav")
File "C:\Users\ukbig\Documents\GitHub\TTS-dataset-tools\dataset_builder.py", line 387, in upload_blob
blob.upload_from_filename(source_file_name)
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\cloud\storage\blob.py", line 2708, in upload_from_filename
self.upload_from_file(
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\cloud\storage\blob.py", line 2567, in upload_from_file
created_json = self._do_upload(
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\cloud\storage\blob.py", line 2384, in _do_upload
response = self._do_resumable_upload(
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\cloud\storage\blob.py", line 2228, in _do_resumable_upload
response = upload.transmit_next_chunk(transport, timeout=timeout)
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\resumable_media\requests\upload.py", line 515, in transmit_next_chunk
return _request_helpers.wait_and_retry(
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\resumable_media\requests_request_helpers.py", line 171, in wait_and_retry
raise error
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\resumable_media\requests_request_helpers.py", line 148, in wait_and_retry
response = func()
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\resumable_media\requests\upload.py", line 507, in retriable_request
result = transport.request(
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\auth\transport\requests.py", line 549, in request
response = super(AuthorizedSession, self).request(
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\requests\sessions.py", line 587, in request
resp = self.send(prep, **send_kwargs)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\requests\sessions.py", line 701, in send
r = adapter.send(request, **kwargs)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\requests\adapters.py", line 547, in send
raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: ('Connection aborted.', timeout('The write operation timed out'))
Uploading Uploading file to cloud storage bucket... to google cloud storage bucket
Traceback (most recent call last):
File "tools.py", line 70, in run_google_speech_call
builder.diarization(get_value("label_wav_file_transcribe"), get_value("input_storage_bucket"), get_value("input_project_name"))
File "C:\Users\ukbig\Documents\GitHub\TTS-dataset-tools\dataset_builder.py", line 395, in diarization
self.upload_blob(bucket_name, wavfile, "temp_audio.wav")
File "C:\Users\ukbig\Documents\GitHub\TTS-dataset-tools\dataset_builder.py", line 387, in upload_blob
blob.upload_from_filename(source_file_name)
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\cloud\storage\blob.py", line 2706, in upload_from_filename
with open(filename, "rb") as file_obj:
FileNotFoundError: [Errno 2] No such file or directory: 'Uploading file to cloud storage bucket...'
Uploading C:\Users\ukbig\Music\JOB/6127495.wav to google cloud storage bucket
Traceback (most recent call last):
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\connectionpool.py", line 703, in urlopen
httplib_response = self._make_request(
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\connectionpool.py", line 398, in _make_request
conn.request(method, url, **httplib_request_kw)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\connection.py", line 239, in request
super(HTTPConnection, self).request(method, url, body=body, headers=headers)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1256, in request
self._send_request(method, url, body, headers, encode_chunked)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1302, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1251, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1050, in _send_output
self.send(chunk)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 972, in send
self.sock.sendall(data)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\ssl.py", line 1204, in sendall
v = self.send(byte_view[count:])
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\ssl.py", line 1173, in send
return self._sslobj.write(data)
socket.timeout: The write operation timed out

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\requests\adapters.py", line 489, in send
resp = conn.urlopen(
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\connectionpool.py", line 787, in urlopen
retries = retries.increment(
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\util\retry.py", line 550, in increment
raise six.reraise(type(error), error, _stacktrace)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\packages\six.py", line 769, in reraise
raise value.with_traceback(tb)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\connectionpool.py", line 703, in urlopen
httplib_response = self._make_request(
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\connectionpool.py", line 398, in _make_request
conn.request(method, url, **httplib_request_kw)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\urllib3\connection.py", line 239, in request
super(HTTPConnection, self).request(method, url, body=body, headers=headers)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1256, in request
self._send_request(method, url, body, headers, encode_chunked)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1302, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1251, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 1050, in _send_output
self.send(chunk)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\http\client.py", line 972, in send
self.sock.sendall(data)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\ssl.py", line 1204, in sendall
v = self.send(byte_view[count:])
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\ssl.py", line 1173, in send
return self._sslobj.write(data)
urllib3.exceptions.ProtocolError: ('Connection aborted.', timeout('The write operation timed out'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "tools.py", line 70, in run_google_speech_call
builder.diarization(get_value("label_wav_file_transcribe"), get_value("input_storage_bucket"), get_value("input_project_name"))
File "C:\Users\ukbig\Documents\GitHub\TTS-dataset-tools\dataset_builder.py", line 395, in diarization
self.upload_blob(bucket_name, wavfile, "temp_audio.wav")
File "C:\Users\ukbig\Documents\GitHub\TTS-dataset-tools\dataset_builder.py", line 387, in upload_blob
blob.upload_from_filename(source_file_name)
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\cloud\storage\blob.py", line 2708, in upload_from_filename
self.upload_from_file(
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\cloud\storage\blob.py", line 2567, in upload_from_file
created_json = self._do_upload(
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\cloud\storage\blob.py", line 2384, in _do_upload
response = self._do_resumable_upload(
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\cloud\storage\blob.py", line 2228, in _do_resumable_upload
response = upload.transmit_next_chunk(transport, timeout=timeout)
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\resumable_media\requests\upload.py", line 515, in transmit_next_chunk
return _request_helpers.wait_and_retry(
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\resumable_media\requests_request_helpers.py", line 171, in wait_and_retry
raise error
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\resumable_media\requests_request_helpers.py", line 148, in wait_and_retry
response = func()
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\resumable_media\requests\upload.py", line 507, in retriable_request
result = transport.request(
File "C:\Users\ukbig\AppData\Roaming\Python\Python38\site-packages\google\auth\transport\requests.py", line 549, in request
response = super(AuthorizedSession, self).request(
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\requests\sessions.py", line 587, in request
resp = self.send(prep, **send_kwargs)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\requests\sessions.py", line 701, in send
r = adapter.send(request, **kwargs)
File "C:\Users\ukbig\anaconda3\envs\myenv\lib\site-packages\requests\adapters.py", line 547, in send
raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: ('Connection aborted.', timeout('The write operation timed out'))

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions