Instructions to use mitchelldehaven/whisper-large-v2-ru with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mitchelldehaven/whisper-large-v2-ru with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="mitchelldehaven/whisper-large-v2-ru")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("mitchelldehaven/whisper-large-v2-ru") model = AutoModelForSpeechSeq2Seq.from_pretrained("mitchelldehaven/whisper-large-v2-ru") - Notebooks
- Google Colab
- Kaggle
Different behaviour of tokenizer
1
#5 opened almost 2 years ago
by
mizoru
translation of the model for use in faster-whisper.
2
#4 opened over 2 years ago
by
boykan
Adding `safetensors` variant of this model
#2 opened over 2 years ago
by
SFconvertbot