Whisper is a general-purpose speech recognition library by OpenAI.
Questions tagged [openai-whisper]
175 questions
2
votes
0 answers
I can´t run WHISPER openai on GPU in vscode
I am having this result for model.device = cpu whith this code. How can i switch to my gpu (laptop msi + nvidia rtx2060)
import whisper
from IPython.display import Audio
model = whisper.load_model("base")
Audio("audioingles.mp3")
print…
Antonio Rojas
- 21
- 1
1
vote
0 answers
Huggingface pipeline with langchain
Hi i am trying to do speaker diarization with open/ai whisper model.
from langchain.llms import HuggingFacePipeline
import torch
from transformers import AutoTokenizer, WhisperProcessor,AutoModelForCausalLM, pipeline, AutoModelForSeq2SeqLM
model_id…
san1
- 455
- 2
- 11
1
vote
1 answer
How can I integrate OpenAI Whisper model into a Kotlin app?
I require guidance on incorporating Whisper OpenAI into my Android application developed with Kotlin in Android Studio. Unfortunately, I haven't come across any relevant instructions or details regarding its installation and utilization in this…
Valentine
- 11
- 2
1
vote
1 answer
FFmpeg installation not detected with diart
Here I'm using the diart library for audio transcription and the OpenAI Whisper model model.
When I run my code I get this error though
Traceback (most recent call last):
File "/home/vkyc/Desktop/projectRasa/audio/lib/python3.10/site-…
Schrödinger's Cat
- 75
- 1
- 6
1
vote
1 answer
Title: I'm encountering a CUDA out of memory error while trying to fine-tune the Whisper model in Arabic using PyTorch
The error message is as follows:CUDA out of memory. Tried to allocate 26.00 MiB (GPU 0; 23.65 GiB total capacity; 21.91 GiB already allocated; 25.56 MiB free; 22.62 GiB reserved in total by PyTorch) If reserved memory is >> allocated memory try…
1
vote
1 answer
Make Whisper use the LAST 30 sec chunk (and not the first)
According to Whisper, the notion is as follows:
Internally, the transcribe() method reads the entire file and processes the audio with a sliding 30-second window, performing autoregressive sequence-to-sequence predictions on each window.
It is…
bonchardon
- 31
- 4
1
vote
0 answers
OpenAI Create Transcription with file sending from Nodejs but it's incorrect
I'm using OpenAI Create Transcription to translate sub from the audio.
So I will upload my audio on Client Web. Then it will send this file to my server.
My server uses Nestjs with Fastify (Fastify Multipart) to get the file. I also use FormData…
Thai Nguyen
- 33
- 4
1
vote
1 answer
Issue with python code using whisper and speech_recognition: NumbaDeprecationWarning
So I was trying to test the whisper openai model, with the speech_recognition module, in python and this error pops up:
NumbaDeprecationWarning: The 'nopython' keyword argument was not supplied to the 'numba.jit' decorator. The implicit default…
Julian Hoffguy
- 11
- 1
1
vote
0 answers
react-native using expo-av IOS mp4 file openai's audio transcriptions invalid file format
I'm getting this back error message back from openai's transcription endpoint
message: "Invalid file format. Supported formats: ['m4a', 'mp3', 'webm', 'mp4', 'mpga', 'wav', 'mpeg']"
Here is my code:
// needed for IoS
if (audioPermission) {
await…
Ibra
- 912
- 1
- 12
- 31
1
vote
0 answers
I this a correct way to send request to whisper api via Ajax
I am getting back a 400 code
what I have to change in order to fix this issue
help....
function sendAudio(chunks){
let blob = new Blob(chunks, { type: "audio/webm; codecs=opus" });
let formData = new FormData();
…
user21763626
- 11
- 1
1
vote
0 answers
PySocks error with Whisper - how to troubleshoot
I am facing an issue where I need to use a microcontroller with Whisper, but due to the slow operation of the microcontroller, I am looking to use an API instead of a local model. Unfortunately, the SDK I am currently using only supports…
mogmol
- 11
- 2
1
vote
2 answers
OpenAI Whisper hangs/freezes on some audio files
I am experiencing issues with OpenAI's whisper and faster-whisper when processing audio files. Specifically, some of the files fail to fully process and the progress bar freezes, occurring randomly across durations. I suspect this issue may be…
Parzival
- 62
- 5
1
vote
0 answers
how to avoid automatic grammar correction in whisper openai
Whisper corrects speech grammar automatically, who has ideas how can I disable that?
this is the code:
const openai = new OpenAIApi(configuration);
const resp = await openai
.createTranscription(
fs.createReadStream(filePath),
…
Sasun Hakobyan
- 15
- 6
1
vote
1 answer
how to use OpenAI Whisper in PHP
I am using php to connect to the whisper interface of openai, but according to the document, I keep reporting errors.
Here is my code:
蒋振东
- 19
- 2
1
vote
0 answers
I have a text file. I generate a voice-over wav file using TTS. How can I generate subtitle for it?
I have a text file. I generate a voice-over wav file using TTS. How can I generate subtitles for it?
I use Azure and/or Coqui-AI TTS depending on the case.
I currently generate subtitles using the offline openai-Whisper model. But, it doesn't…
Serhan
- 11
- 2