Downloads · 30 days
29
51% of all-time downloads
zionia/whisper-small-isizulu-noisy
whisper-small-isizulu-noisy is a automatic speech recognition model from zionia. Use it when you need speech turned into text. The card lists the license as apache-2.0.
This model is a fine-tuned version of openai/whisper-small on multiple South African language datasets.
Downloads · 30 days
29
51% of all-time downloads
All-time downloads
57
Public
Parameters
242M
14.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.pt5.8 GB · 60%
From the Hugging Face model README
This model is a fine-tuned version of openai/whisper-small on multiple South African language datasets.
This model was trained on 2 combined datasets:
Total training samples: 1050 Total test samples: 263
from transformers import pipeline
pipe = pipeline("automatic-speech-recognition", model="zionia/whisper-small-isizulu-noisy")
result = pipe("path/to/audio.wav")