All Questions
Tagged with openai-whisper pytorch
16 questions
0
votes
0
answers
62
views
Issue with Data Preprocessing and Tensor Concatenation for Whisper Model Training
I am trying to train a Whisper model for Jeju dialect speech recognition. However, I am encountering several errors related to tensor concatenation during the data preprocessing phase. Below is the ...
- 1
1
vote
0
answers
654
views
Where is the Bottleneck for multiple requests using Whisper on Nvidia A100
I want to use Whisper-Large-v3 (Speech-to-Text) for a real-time application. However, I want to process several requests at the same time. My Whisper instance runs on an Nvidia A100 with 80GB VRAM.
In ...
- 11
2
votes
1
answer
4k
views
RuntimeError: Library cublas64_12.dll is not found or cannot be loaded. While using WhisperX diarization
I was trying to use whisperx to do speaker diarization. I did it sucessfully on google colab but I'm encountering this error while tyring to transcribe the audio file.
Traceback (most recent call last)...
- 23
0
votes
0
answers
257
views
How to optimise Hyperparameters for Whisper finetuning?
I am currently working on a project where I would like to fine-tune a whisper model via the HuggingFace Transformers library. So far, the finetuning has worked well, however, I have become stuck on ...
- 1
1
vote
0
answers
156
views
convert a whisper-small.pt model to hugging face through convert_openai_to_hf.py
I have a problem I want to convert a file with the extension .pt to CTranslate2. To do that, you first need to convert it to hugging face and then execute a command line that will convert the file ...
- 11
1
vote
2
answers
5k
views
RuntimeError: Library libcublas.so.11 is not found or cannot be loaded
I am working on an LLM project on google colab using V100 GPU, High-RAM mode, and these are my dependencies:
git+https://github.com/pyannote/pyannote-audio
git+https://github.com/huggingface/...
- 41
0
votes
1
answer
1k
views
Load and unload model on celery worker
I currently have a system that initiates tasks on whisper AI model using Celery. However, the existing setup involves loading the model inside each task, which is suboptimal due to the repeated ...
- 87
0
votes
1
answer
3k
views
Converting a hugging face model into complete .pt file
I have downloaded a Hugging Face model, and it comes with various files, including pytorch_model.bin, config.json, and others. My goal is to integrate this model into my project, and I would like to ...
2
votes
0
answers
434
views
CUDA/GPU not being utilized
I am trying to use pyannote.audio for diarization and then use Whisper for transcription.
I have two machines: one with RTX3050 Laptop GPU, another is my desktop with 2060 Super. When I am running my ...
1
vote
0
answers
361
views
OpenAI Whisper terminates immediately after running
I have a fresh Arch linux box with fresh install of both pytorch and whisper. When I try to use whisper on an audio file I get an error:
$ whisper pytorch_env/pistol.mp3 --model base
fish: Job 1, '...
-1
votes
1
answer
160
views
Whisper Zoo model on DJL with GPU: Getting error "c10::intrusive_ptr<c10::TensorImpl, c10::UndefinedTensorImpl>::operator->() const+0xc"
I'm trying to run the Whisper zoo model from DJL examples in GPU.
In the first run, I got the error that two devices were found - Cuda and CPU.
As I understood that this error occurs due to just the ...
- 47
1
vote
0
answers
376
views
I could not able to install PyTorch on raspberry is there a PyTorch version which can be installed on raspberry pi 3b+?
I could not able to install PyTorch on raspberry is there a PyTorch version which can be installed on raspberry pi 3b+?
I tried diffrent version and none worked for me
I tried official sites other ...
- 21
0
votes
1
answer
5k
views
Unable to utilize GPU for whisper AI. Only using CPU
I am using WhisperAI from OpenAI to transcribe english and french audio. Git link here. I followed their instructions to install WhisperAI
The instance has a GPU, but torch.cuda.is_available() keeps ...
- 3
1
vote
1
answer
2k
views
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) ...
5
votes
0
answers
1k
views
How to load a pytorch model directly to the GPU
I'm trying to load the whisper large v2 model into a GPU but in order to do that, it seems that pytorch unpickle the whole model using CPU's RAM using more than 10GB of memory, and then it load's it ...
- 342
0
votes
0
answers
1k
views
Parallel inference on single model in CUDA cause worker processes to terminate
I'm trying to start openai\whisper inference on single model in CUDA with multiprocessing.Pool.
On 6 workers inference works fine, except of some CUDA warnings on exiting worker processes.
On 7 and ...
- 1