Automatic Speech Recognition
Transformers
PyTorch
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results
Instructions to use openai/whisper-large-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-large-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large-v3")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-large-v3") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-large-v3") - Inference
- Notebooks
- Google Colab
- Kaggle
finetuning whisper large on google colab - pro or pro+ which one is best?
#166
by andromeda01111 - opened
I am trying to train the whisper large v3 on google colab. Confused about colab pro and colab pro+.
which is more suitable for training on a dataset of 8k audio files, each audio file is 4 seconds long.
andromeda01111 changed discussion title from Possibility of fine tuning whisper_large-v3 on mac or intel gpu s? to finetuning whisper large on google colab - pro or pro+ which one is best?
So I tried colab pro with 100 computational units. But ran out of computational units so I would say pro is definitely not enough for me. If anyone had successfully finetuned whisper-large-v3 on google colab please share details like number of computational details, gpu type and memory, dataset details, etc.
gave up on google colab.
andromeda01111 changed discussion status to closed