Can't transcribe local audio file and got error message.

[wuzimi]

C:\Users\Administrator>python deepgram_test.py futrelife.mp3
Initializing Deepgram SDK...
SDK Initialized.
Transcribing audio file...
Traceback (most recent call last):
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\urllib\request.py", line 1348, in do_open
h.request(req.get_method(), req.selector, req.data, headers,
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\http\client.py", line 1283, in request
self._send_request(method, url, body, headers, encode_chunked)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\http\client.py", line 1329, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\http\client.py", line 1278, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\http\client.py", line 1077, in _send_output
self.send(chunk)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\http\client.py", line 999, in send
self.sock.sendall(data)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\ssl.py", line 1237, in sendall
v = self.send(byte_view[count:])
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\ssl.py", line 1206, in send
return self._sslobj.write(data)
ssl.SSLEOFError: EOF occurred in violation of protocol (_ssl.c:2426)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\site-packages\deepgram_utils.py", line 139, in attempt
with urllib.request.urlopen(req) as resp:
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\urllib\request.py", line 216, in urlopen
return opener.open(url, data, timeout)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\urllib\request.py", line 519, in open
response = self._open(req, data)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\urllib\request.py", line 536, in _open
result = self._call_chain(self.handle_open, protocol, protocol +
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\urllib\request.py", line 496, in _call_chain
result = func(*args)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\urllib\request.py", line 1391, in https_open
return self.do_open(http.client.HTTPSConnection, req,
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\urllib\request.py", line 1351, in do_open
raise URLError(err)
urllib.error.URLError: <urlopen error EOF occurred in violation of protocol (_ssl.c:2426)>

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\Administrator\deepgram_test.py", line 54, in
main()
File "C:\Users\Administrator\deepgram_test.py", line 48, in main
response = dg_client.transcription.sync_prerecorded(source, options)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\site-packages\deepgram\transcription.py", line 355, in sync_prerecorded
return SyncPrerecordedTranscription(
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\site-packages\deepgram\transcription.py", line 111, in call
return _sync_request(
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\site-packages\deepgram_utils.py", line 153, in _sync_request
return attempt()
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\site-packages\deepgram_utils.py", line 148, in attempt
raise (Exception(f'DG: {exc}') if exc.status < 500 else exc)
AttributeError: 'URLError' object has no attribute 'status'

[briancbarrow]

@wuzimi Can you provide the code you used when running this? Did you copy the code from the console and run it or did you make modifications?

[acerock6]

getting the same error, on MacOS Ventura 13.3.1. Below is the code:

from deepgram import Deepgram
import json

# Replace with your file path and audio mimetype
PATH_TO_FILE = '~/xx/xx/xxx.m4a'
MIMETYPE = 'audio/mp4'


# Initializes the Deepgram SDK
dg_client = Deepgram(DEEPGRAM_API_KEY)

with open(PATH_TO_FILE, 'rb') as audio:
    source = {'buffer': audio, 'mimetype': MIMETYPE}
    options = { "punctuate": True, "model": "enhanced", "language": "en-IN" }

    print('Requesting transcript...')
    print('Your file may take up to a couple minutes to process.')
    print('While you wait, did you know that Deepgram accepts over 40 audio file formats? Even MP4s.')

    response = dg_client.transcription.sync_prerecorded(source, options)
    print(json.dumps(response, indent=4))

[shirgoldbird]

Hey @acerock6! The issue is that you're specifying an invalid model. enhanced is one of our tiers, and it has models like general and phonecall associated with it. So you could say "model": "general", "tier": "enhanced".

However, the en-IN language is not available for the enhanced tier. It is available on our base or nova tiers. A working set of options would be:

options = { "punctuate": True, "model": "general", "tier": "nova", "language": "en-IN" }

Check out our documentation for Language and Tier to learn more.

[acerock6]

Got it, thanks for clarifying.