Instructions to use waveletdeboshir/whisper-tiny-ru-pruned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use waveletdeboshir/whisper-tiny-ru-pruned with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="waveletdeboshir/whisper-tiny-ru-pruned")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("waveletdeboshir/whisper-tiny-ru-pruned") model = AutoModelForSpeechSeq2Seq.from_pretrained("waveletdeboshir/whisper-tiny-ru-pruned") - Notebooks
- Google Colab
- Kaggle
Update model and tokenizer
#1
by waveletdeboshir - opened
Now there are no timestamp and language tokens (except ru and en) in tokenizer, merges.txt is modified.
Instead of timestamps tokens I added more Russian tokens.