Automatic Speech Recognition
Transformers
JAX
TensorBoard
ONNX
Safetensors
Transformers.js
English
whisper
audio
Eval Results
Instructions to use distil-whisper/distil-large-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use distil-whisper/distil-large-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="distil-whisper/distil-large-v3")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("distil-whisper/distil-large-v3") model = AutoModelForMultimodalLM.from_pretrained("distil-whisper/distil-large-v3") - Transformers.js
How to use distil-whisper/distil-large-v3 with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('automatic-speech-recognition', 'distil-whisper/distil-large-v3'); - Notebooks
- Google Colab
- Kaggle
GGML format please!
#8
by dnhkng - opened
Could we get this model in GGML, as for V2?
Or at least the conversion script :)
Thanks!
You can find some GGUF quants here: https://huggingface.co/FL33TW00D-HF/distil-whisper-large-v3/tree/main
GGML can be created using tensor-tools in candle whilst the script isn't integrated: https://github.com/huggingface/candle/tree/main/tensor-tools
GGML weights are available at: https://huggingface.co/distil-whisper/distil-large-v3-ggml
See instructions on README for running in Whisper.cpp: https://huggingface.co/distil-whisper/distil-large-v3#whispercpp