Develop Reference

Whisper Module Python Speech to Text

I'm just trying to create a simple speech to text transcriber using the openai whisper module and streamlit for web application but having some problems.
It is giving me error
Traceback (most recent call last):
File "C:\Users\Satyam Singh\AppData\Local\Programs\Python\Python310\lib\site-packages\streamlit\runtime\scriptrunner\script_runner.py", line 565, in _run_script
exec(code, module.__dict__)
File "C:\Users\Satyam Singh\Desktop\Python Project\app.py", line 19, in <module>
transcription = model.transcribe(audio_file)
File "C:\Users\Satyam Singh\AppData\Local\Programs\Python\Python310\lib\site-packages\whisper\transcribe.py", line 84, in transcribe
mel = log_mel_spectrogram(audio)
File "C:\Users\Satyam Singh\AppData\Local\Programs\Python\Python310\lib\site-packages\whisper\audio.py", line 112, in log_mel_spectrogram audio = torch.from_numpy(audio)
**TypeError: expected np.ndarray (got NoneType)**
Here's my code
import streamlit as st
import whisper
from audio_recorder_streamlit import audio_recorder
# App Title Name
st.title("Speech to Text")
# uploading an audio file
# audio_file = st.file_uploader("Upload Audio", type=["wav","mp3","m4a"])
audio_file = audio_recorder()
if audio_file:
st.audio(audio_file, format="audio/wav")
model = whisper.load_model("base")
st.text("Whisper Model Loaded")
transcription = model.transcribe(audio_file)
print(transcription['text'])
if st.sidebar.button("Transcribe Audio"):
if audio_file is not None:
st.sidebar.success("Transcribing Audio")
transcription = model.transcribe(audio_file.name)
st.sidebar.success("Transcription Complete")
st.text(transcription["text"])
else:
st.sidebar.error("Please Upload an Audio File")
I want something like Baseten
I want this code to work or something more innovative which works same way like this one or Baseten.

Why does this code only work intermittently? Sometimes I get an error that I can't find on Google

I'm using the below code to connect to the Google BigQuery API. It only works intermittently. After this part, I attempt to send a dataframe to a BQ table via the "to_gbq" function. That part also only sometimes works, and other times fails due to the same error message.
Code:
from google.cloud import bigquery
from google.oauth2 import service_account
path_to_json = 'gbq_key.json'
my_credentials = service_account.Credentials.from_service_account_file(path_to_json)
my_project = 'myprojectnameishere'
client = bigquery.Client(credentials=my_credentials, project=my_project)
print('connected')
AttributeError: module 'google.api_core' has no attribute 'client_options'
Detailed error:
File "/home/my_user_name/get_mini_bq_helper.py", line 8, in <module>
client = bigquery.Client(credentials=my_credentials, project=my_project)
File "/home/my_user_name/.local/lib/python3.10/site-packages/google/cloud/bigquery/client.py", line 226, in __init__
super(Client, self).__init__(
File "/home/my_user_name/.local/lib/python3.10/site-packages/google/cloud/client/__init__.py", line 321, in __init__
Client.__init__(
File "/home/my_user_name/.local/lib/python3.10/site-packages/google/cloud/client/__init__.py", line 157, in __init__
client_options = google.api_core.client_options.ClientOptions()
AttributeError: module 'google.api_core' has no attribute 'client_options'
I am hosting this on PythonAnywhere but I randomly get this error locally as well. Sometimes it connects with no issue, but most of the time I get this error. Also, I couldn't find this error anywhere on Google/Stack Overflow. Any ideas what it might be?

Adafruit MAX 31856 communicating with raspberrypi

I have been trying to read a thermocouple temperature on my raspberrypi however cant get the raspi to communicate with the adafruit MAX 31856. I have downloaded necessary libraries and checked that all connections are secure and correct however keep running into this error when I try to execute this code.
Any help is greatly appreciated!!
CODE
import board
import digitalio
import adafruit_max31856
spi = board.SPI()
cs = digitalio.DigitalInOut(board.D5)
cs.direction = digitalio.Direction.OTUPUT
thermocouple = adafruit_max31856.MAX31856(spi,cs)
print(thermocouple.temperature)
ERROR:
Traceback (most recent call last):
File "/home/pi/test4.py", line 6, in <module>
spi = board.SPI()
File "/usr/local/lib/python3.7/dist-packages/board.py", line 299, in SPI
return busio.SPI(SCLK, MOSI, MISO)
File "/usr/local/lib/python3.7/dist-packages/busio.py", line 289, in __init__
self._spi = _SPI(portId)
File "/usr/local/lib/python3.7/dist-packages/adafruit_blinka/microcontroller/generic_linux/spi.py", line 25, in __init__
self._spi = spi.SPI(device=(portid, 0))
File "/usr/local/lib/python3.7/dist-packages/Adafruit_PureIO/spi.py", line 167, in __init__
raise IOError("{} does not exist".format(device))
OSError: /dev/spidev0.0 does not exist
Code
Errors

Most probably there is a device driver loaded for spi0-0 and that removes /dev/spidev0.0 device.
check your /boot/config.txt for overlays loading MAX 31856 driver module.
if you want to use adafruit_max31856 lib you shouldn't be loading this driver. hope that helps

KeyError: 'type' Clarifai

I'm starting on a project using Clarifai. However, when I define the app, I'm getting a key error:
from clarifai.rest import ClarifaiApp
from clarifai.rest import Image as ClImage
import os
from glob import glob
api_key = 'my api key'
app = ClarifaiApp(api_key=api_key) # Error occurs here
model_id = 'model id'
concepts = ['concept1', 'concept2', 'concept3']
Traceback (most recent call last):
File "C:\Users\crayo\uShoe\main.py", line 6, in <module>
app = ClarifaiApp(api_key=api_key)
File "C:\Users\user\project\venv\lib\site-packages\clarifai\rest\client.py", line 124, in __init__
self.models = Models(self.api, self.solutions) # type: Models
File "C:\Users\user\project\venv\lib\site-packages\clarifai\rest\client.py", line 1068, in __init__
self.model_id_cache = self.init_model_cache()
File "C:\Users\user\project\venv\lib\site-packages\clarifai\rest\client.py", line 1088, in init_model_cache
model_type = m.output_info['type']
KeyError: 'type'
I'm not sure what's causing this error, so if someone could provide input I'd appreciate it! Thanks!

You are using the deprecated Python REST package: https://github.com/Clarifai/clarifai-python. Please replace your code with the new & updated Python gRPC client: https://github.com/Clarifai/clarifai-python-grpc
Make sure to uninstall the REST package to avoid conflicts.
You can find our API docs & code snippets here: https://docs.clarifai.com

Attribute error in python with Google Speech API

'str' object has no attribute 'long_running_recognize'. This error is occurring at the last line of the code shown. I jump into the code and see no obvious reason for it to fail. Jumps out at the wrap_method below.
if "long_running_recognize" not in self._inner_api_calls:
self._inner_api_calls[
"long_running_recognize"
] = google.api_core.gapic_v1.method.wrap_method(
self.transport.long_running_recognize,
default_retry=self._method_configs["LongRunningRecognize"].retry,
default_timeout=self._method_configs["LongRunningRecognize"].timeout,
client_info=self._client_info,
)
The only issue that I could conceive here is maybe the audio file is too large(45mb...53 min). But the code break happens in a location that doesn't appear to relate to this.
import io
import os
from google.cloud import speech
from google.cloud.speech import enums
from google.cloud.speech import types
with open("path\\My First Project-edb18653fedf.json") as f:
GOOGLE_APPLICATION_CREDENTIALS = f.read()
client = speech.SpeechClient(GOOGLE_APPLICATION_CREDENTIALS)
file_path = "audio\\102.flac"
with io.open(file_path, 'rb') as audio_file:
content = audio_file.read()
audio = types.RecognitionAudio(content=content)
config = types.RecognitionConfig(
encoding=enums.RecognitionConfig.AudioEncoding.FLAC,
sample_rate_hertz=32000,
language_code='en-US')
operation = client.long_running_recognize(config, audio)
Connected to pydev debugger (build 191.7479.30)
Traceback (most recent call last):
File "C:\Program Files\JetBrains\PyCharm Community Edition 2019.1.2\helpers\pydev\pydevd.py", line 1758, in <module>
main()
File "C:\Program Files\JetBrains\PyCharm Community Edition 2019.1.2\helpers\pydev\pydevd.py", line 1752, in main
globals = debugger.run(setup['file'], None, None, is_module)
File "C:\Program Files\JetBrains\PyCharm Community Edition 2019.1.2\helpers\pydev\pydevd.py", line 1147, in run
pydev_imports.execfile(file, globals, locals) # execute the script
File "C:\Program Files\JetBrains\PyCharm Community Edition 2019.1.2\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "C:/Users/shear/Documents/PythonScripts/GStTEnv/SpeechToText/CloudSpeechText.py", line 105, in <module>
operation = client.long_running_recognize(config, audio)
File "C:\Users\shear\GStTEnv\lib\site-packages\google\cloud\speech_v1\gapic\speech_client.py", line 314, in long_running_recognize
self.transport.long_running_recognize,
AttributeError: 'str' object has no attribute 'long_running_recognize'

Did you try to prove out your theory about the length of the audio? What happens if you trim the audio and try it?
Does it happen if you try a curl request at the command line instead of code?
I’d like to see if I can help. To diagnose further, would you be able to provide:
- Exact steps to reproduce
- Pointer to github repo if available
- As much of the code as you can provide
- Exact error messages
- Language Code (config)
- All configuration options applicable
- Sample audio file with all personal data removed (on Google Drive or Cloud Storage)