Whisper is a general-purpose speech recognition library by OpenAI.
Questions tagged [openai-whisper]
175 questions
0
votes
0 answers
Gradio - Running Parallel ASW models
I am trying to run parallel models on Gradio for the ASR.
I am loading the base model and I have 2 transcribe methods for each model, but in this case it is the same model for testing purposes. When I run it with the single interface on the Parallel…
Baradwaj Aryasomayajula
- 1,184
- 1
- 16
- 42
0
votes
1 answer
OpenAI Whisper API: Get token/minute usage from response
I am using openAI whisper to convert voice to text: https://platform.openai.com/docs/api-reference/audio/create
the json response is
{
"text": "some text"
}
the response data return only one text field and has no other information
I want to know…
Acid Coder
- 2,047
- 15
- 21
0
votes
1 answer
Apache server configuration for Whisper OpenAI
Good afternoon,
I have installed Whisper from OpenAI on a Linux server with Ubuntu and Apache as web server. I followed the tutorial in the README.md file hosted in https://huggingface.co/spaces/aadnk/whisper-webui using python.
When I access via…
0
votes
1 answer
how to use OpenAI Whisper in C#
I'm new in C#
i want to make voice assistant in C# and use Whisper for Speech-To-Text.
I want use IronPython for use python in c# because I can't use Whisper in C#.
this is my python code:
import replicate
import…
yasin gahan tigh
- 1
- 1
- 2
0
votes
1 answer
Simple import is throwing an error; any ideas on why I'm not able to import whisper using python?
I was able to successfully run my code earlier today, but as of this evening I am getting a syntax error when trying to import Whisper. Any ideas?
line 9, in
import whisper
File…
maruchan105
- 15
- 4
0
votes
1 answer
How to set whisper.DecodingOptions language?
I'm trying to run whisper and I want to set the DecodingOptions.language with France (instead of using it's language detection).
I have tried to write:
options = whisper.DecodingOptions()
options.language = "fr"
but I'm getting…
user3668129
- 4,318
- 6
- 45
- 87
0
votes
0 answers
Whisper accurate timestamps on russian language?
I have problems with making consistent and precise openAi-Whisper timestamps. I am currently looking for a way to receive better timestamping on Russian language using Whisper. I am using pre-made samples where the phrases are separated by 1 sec…
Oleg Shindelov
- 15
- 5
0
votes
0 answers
Whisper GPU implementation
I am new to whisper.
I am trying to run a program of whisper openai using GPU.
My system details
OS: Ubuntu GPU: Radeon Instinct MI25 MxGPU
Since cant use CUDA, is there any other options available ?
Thanks in advance
user3086306
- 7
- 4
0
votes
0 answers
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…
Satyam Singh
- 1
- 2
0
votes
0 answers
What is a simple way to do longform transcription/translation/subtitles with Whisper using a downloaded custom model?
Using custom model downloaded from HuggingFace appears to be either far more difficult than I'd expect it to be, or far less useful and less featureful than just using Whisper from the command line or the .transcribe() method of the basic Whisper…
Chris Prokop
- 1
- 1
0
votes
1 answer
How to pass InMemoryUploadedFile as a file?
User records audio, audio gets saved into audio Blob and sent to backend. I want to get the audio file and send it to openai whisper API.
files = request.FILES.get('audio')
audio = whisper.load_audio(files)
I've tried different ways to send…
IonicEcommerce
- 69
- 8
0
votes
0 answers
What is the data inside AudioData? (OpenAI Whisper)
I am trying to understand what the output of audio2 is. When I print it, all I get is its location. However, I would like to know specifically what type of data is located inside audio2 and what type of input is required for the recognize_google()…
Ariel Makovoz
- 1
- 2
0
votes
0 answers
Whisper module cannot accept my AudioData
I attempted to use the SpeechRecognition library to decode Audio into Text. I used the recognize_whisper function to transmit the audio into text. However, I keep getting an error.
CODE:
import speech_recognition as sr
import pyttsx3
import…
Ariel Makovoz
- 1
- 2
0
votes
0 answers
How to speed up a while loop using invoke() in tensorflow?
Some context: I am trying to convert the whisper decoder to tensorflow-lite and so far all works, but the result is slow. My decoder looks as follow:
import numpy as np
import tensorflow as tf
class TfliteDecoder:
def __init__(self,…
SuperKogito
- 2,998
- 3
- 16
- 37
0
votes
1 answer
No file or directory: 'ffmpeg' on MacOS in Python
I am using MacOS (Apple Silicon) and I am trying to use the whisper module from OpenAI in Python. My code is this:
import whisper
file_path = "4547.mp3"
model = whisper.load_model("base")
result =…
Harper Bledsoe
- 31
- 5