Tuesday, June 6, 2023

Ecoute Installation and Introduction for Transcription - Step by Step

Following is step by step instruction as how to install Ecoute AI tool for live transcription that provides real time transcripts for both microphone input and speakers output. There are lot of use cases for Ecoute in Job interview training for example.

Commands used in video to install ecoute on Windows:


  • Chocolatey
  • Python >=3.8.0
  • An OpenAI API key
  • Windows OS (Not tested on others)
  • FFmpeg

Step 1: Install Chocolaty

Open Powershell as administrator and run following in powershell window:

Set-ExecutionPolicy Bypass -Scope Process -Force; [System.Net.ServicePointManager]::SecurityProtocol = [System.Net.ServicePointManager]::SecurityProtocol -bor 3072; iex ((New-Object System.Net.WebClient).DownloadString('https://community.chocolatey.org/install.ps1'))

Step 2: Install FFMPEG which is audio and video converter.

choco install ffmpeg

Step 3: Clone ecoute repo

git clone https://github.com/SevaSk/ecoute
cd ecoute
pip install -r requirements.txt

Step 4: Get free Open API Key from https://platform.openai.com/account/api-keys

Step 5: Create keys.py file in ecoute folder and insert following in that file.


Step 6: Run the ecoute AI

python main.py --api

Reference: https://github.com/SevaSk/ecoute


Laxmipriya said...

Hello Guyz I have also created a website on which I update about new AI Tool, their features and Prices. Pls checkout: Toolstote: AI Tools

SMMOIN111 said...

I AM STUCK AT THIS git clone https://github.com/SevaSk/ecoute


git : The term 'git' is not recognized as the name of a cmdlet, function, script file, or operable program. Check the
spelling of the name, or if a path was included, verify that the path is correct and try again.
At line:1 char:1
+ git clone https://github.com/SevaSk/ecoute
+ ~~~
+ CategoryInfo : ObjectNotFound: (git:String) [], CommandNotFoundException
+ FullyQualifiedErrorId : CommandNotFoundException

Bhumit said...

just download zip from the link and paste the code.

pankaj said...

i stuck on this

D:\ecoute\ecoute>python main.py --ap
Traceback (most recent call last):
File "D:\ecoute\ecoute\main.py", line 2, in
from AudioTranscriber import AudioTranscriber
File "D:\ecoute\ecoute\AudioTranscriber.py", line 1, in
import whisper
ModuleNotFoundError: No module named 'whisper'

1111 said...

@pankaj pip install openai-whisper --no-cache-dir

Nati said...

I installed everything and firstly it worked but when I tried to launch it next time the System showed me this:
C:\Users\wwwso\ecoute>python main.py --api
C:\Python311\Lib\site-packages\whisper\timing.py:57: NumbaDeprecationWarning: The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details.
[INFO] Adjusting for ambient noise from Default Mic. Please make some noise from the Default Mic...
[INFO] Completed ambient noise adjustment for Default Mic.
[INFO] Adjusting for ambient noise from Default Speaker. Please make or play some noise from the Default Speaker...
[INFO] Completed ambient noise adjustment for Default Speaker.
Incorrect API key provided: API KEY. You can find your API key at https://platform.openai.com/account/api-keys.
Incorrect API key provided: API KEY. You can find your API key at https://platform.openai.com/account/api-keys.
Please advize me what I should do next. Thank you!