Automatic Speech Recognition
Transformers
PyTorch
Kinyarwanda
whisper
STT
fine-tune-kinyarwanda
kinyarwanda
Instructions to use mbazaNLP/Whisper-Small-Kinyarwanda with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mbazaNLP/Whisper-Small-Kinyarwanda with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="mbazaNLP/Whisper-Small-Kinyarwanda")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("mbazaNLP/Whisper-Small-Kinyarwanda") model = AutoModelForSpeechSeq2Seq.from_pretrained("mbazaNLP/Whisper-Small-Kinyarwanda") - Notebooks
- Google Colab
- Kaggle
Update model card: Intended Use, Limitations, code example, BibTeX, licence/email/description fixes
#4 opened 14 days ago
by
rdelyon
how we can use the large model
#3 opened about 1 year ago
by
Aliktk
Adding `safetensors` variant of this model
#2 opened over 1 year ago
by
SFconvertbot
Could you please suggest how to fine-tune the model on top of Swahili
3
#1 opened about 3 years ago
by
nathanhunt